Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.9387. Min Act: -0.1700
Data Index: 7822930 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.5950. Min Act: -0.1700
Data Index: 307968 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.5637. Min Act: -0.1700
Data Index: 7225688 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.5637. Min Act: -0.1700
Data Index: 281524 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.5637. Min Act: -0.1700
Data Index: 4881269 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.5325. Min Act: -0.1700
Data Index: 7958329 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4700. Min Act: -0.1700
Data Index: 5377748 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4700. Min Act: -0.1700
Data Index: 7351098 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4700. Min Act: -0.1700
Data Index: 6432495 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4700. Min Act: -0.1700
Data Index: 404283 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4700. Min Act: -0.1700
Data Index: 3956450 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4387. Min Act: -0.1700
Data Index: 6129166 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4387. Min Act: -0.1700
Data Index: 2047710 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4387. Min Act: -0.1700
Data Index: 5798795 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4075. Min Act: -0.1700
Data Index: 2798844 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.3762. Min Act: -0.1700
Data Index: 7701944 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4075. Min Act: -0.1700
Data Index: 566239 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4075. Min Act: -0.1700
Data Index: 5760194 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.4075. Min Act: -0.1700
Data Index: 6006317 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9387. Min Range: -6.9387
Max Act: 6.3762. Min Act: -0.1700
Data Index: 970843 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19