Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.5059. Min Act: -0.1700
Data Index: 1361738 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.5059. Min Act: -0.1700
Data Index: 3492624 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.5059. Min Act: -0.1700
Data Index: 4105713 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.5059. Min Act: -0.1700
Data Index: 7653657 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.4434. Min Act: -0.1700
Data Index: 410959 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.4434. Min Act: -0.1700
Data Index: 1459141 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3809. Min Act: -0.1700
Data Index: 959998 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3809. Min Act: -0.1700
Data Index: 4611622 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3809. Min Act: -0.1700
Data Index: 874833 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.4434. Min Act: -0.1700
Data Index: 6465200 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3184. Min Act: -0.1700
Data Index: 8003677 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3184. Min Act: -0.1700
Data Index: 2306999 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3184. Min Act: -0.1700
Data Index: 8519490 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3184. Min Act: -0.1700
Data Index: 4428571 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3184. Min Act: -0.1700
Data Index: 652436 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.3184. Min Act: -0.1700
Data Index: 5325111 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.2559. Min Act: -0.1700
Data Index: 2535612 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.2559. Min Act: -0.1700
Data Index: 6194972 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.1934. Min Act: -0.1700
Data Index: 6436384 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5059. Min Range: -10.5059
Max Act: 10.2559. Min Act: -0.1700
Data Index: 7810655 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19