Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.2809. Min Act: -0.1700
Data Index: 3311546 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0934. Min Act: -0.1700
Data Index: 8770866 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0622. Min Act: -0.1700
Data Index: 6529570 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0309. Min Act: -0.1700
Data Index: 8616760 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0309. Min Act: -0.1700
Data Index: 6995993 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2809. Min Range: -5.2809
Max Act: 5.0309. Min Act: -0.1700
Data Index: 58381 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9684. Min Act: -0.1700
Data Index: 868062 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.9684. Min Act: -0.1700
Data Index: 2701469 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8747. Min Act: -0.1700
Data Index: 611110 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8747. Min Act: -0.1700
Data Index: 6992593 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8434. Min Act: -0.1700
Data Index: 3661416 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8434. Min Act: -0.1700
Data Index: 7229919 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.7809. Min Act: -0.1700
Data Index: 2339230 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8122. Min Act: -0.1700
Data Index: 7133047 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8122. Min Act: -0.1700
Data Index: 1964259 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8122. Min Act: -0.1700
Data Index: 5924084 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.8122. Min Act: -0.1700
Data Index: 6413352 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.7809. Min Act: -0.1700
Data Index: 8592841 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.7809. Min Act: -0.1700
Data Index: 6164536 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2809. Min Range: -5.2809
Max Act: 4.7809. Min Act: -0.1700
Data Index: 2908143 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19