Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4335 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.5193. Min Act: -0.1700
Data Index: 401783 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.3318. Min Act: -0.1700
Data Index: 5269171 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.3318. Min Act: -0.1700
Data Index: 591401 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.1756. Min Act: -0.1700
Data Index: 5307234 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.1443. Min Act: -0.1700
Data Index: 3199416 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0818. Min Act: -0.1700
Data Index: 3219485 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0818. Min Act: -0.1700
Data Index: 3738985 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0818. Min Act: -0.1700
Data Index: 3062694 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0506. Min Act: -0.1700
Data Index: 255601 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0193. Min Act: -0.1700
Data Index: 5896120 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0193. Min Act: -0.1700
Data Index: 4731099 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5193. Min Range: -5.5193
Max Act: 5.0193. Min Act: -0.1700
Data Index: 927720 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9881. Min Act: -0.1700
Data Index: 5903154 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9881. Min Act: -0.1700
Data Index: 8008615 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9881. Min Act: -0.1700
Data Index: 1335657 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9881. Min Act: -0.1700
Data Index: 2172279 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9568. Min Act: -0.1700
Data Index: 8211898 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9881. Min Act: -0.1700
Data Index: 583587 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9881. Min Act: -0.1700
Data Index: 5753978 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5193. Min Range: -5.5193
Max Act: 4.9881. Min Act: -0.1700
Data Index: 7476061 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19