Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4940 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0059. Min Range: -8.0059
Max Act: 8.0059. Min Act: -0.1700
Data Index: 1147223 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0059. Min Range: -8.0059
Max Act: 8.0059. Min Act: -0.1700
Data Index: 2757779 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0059. Min Range: -8.0059
Max Act: 8.0059. Min Act: -0.1700
Data Index: 4150208 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.8809. Min Act: -0.1700
Data Index: 1360907 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.8809. Min Act: -0.1700
Data Index: 5462710 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.8184. Min Act: -0.1700
Data Index: 279396 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.7559. Min Act: -0.1700
Data Index: 6401593 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.7559. Min Act: -0.1700
Data Index: 1647855 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.7247. Min Act: -0.1700
Data Index: 3457147 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.7247. Min Act: -0.1700
Data Index: 8632242 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.6934. Min Act: -0.1700
Data Index: 5463746 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.6934. Min Act: -0.1700
Data Index: 8081787 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.6622. Min Act: -0.1700
Data Index: 1619870 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.6622. Min Act: -0.1700
Data Index: 7061583 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.6309. Min Act: -0.1700
Data Index: 2584322 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5997. Min Act: -0.1700
Data Index: 5995457 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5997. Min Act: -0.1700
Data Index: 7619841 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5997. Min Act: -0.1700
Data Index: 8092450 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5997. Min Act: -0.1700
Data Index: 5501669 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5372. Min Act: -0.1700
Data Index: 4542995 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19