Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5353. Min Range: -6.5353
Max Act: 6.5353. Min Act: -0.1700
Data Index: 8689065 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5353. Min Range: -6.5353
Max Act: 6.3791. Min Act: -0.1700
Data Index: 4489411 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5353. Min Range: -6.5353
Max Act: 6.1291. Min Act: -0.1700
Data Index: 6216376 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5353. Min Range: -6.5353
Max Act: 6.0978. Min Act: -0.1700
Data Index: 4937980 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5353. Min Range: -6.5353
Max Act: 6.0353. Min Act: -0.1700
Data Index: 6812099 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5353. Min Range: -6.5353
Max Act: 6.0353. Min Act: -0.1700
Data Index: 2334225 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5353. Min Range: -6.5353
Max Act: 6.0041. Min Act: -0.1700
Data Index: 493817 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.9416. Min Act: -0.1700
Data Index: 6452106 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.9416. Min Act: -0.1700
Data Index: 1371506 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.9103. Min Act: -0.1700
Data Index: 6649442 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.9103. Min Act: -0.1700
Data Index: 7427995 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8791. Min Act: -0.1700
Data Index: 6309056 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8791. Min Act: -0.1700
Data Index: 2029891 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8791. Min Act: -0.1700
Data Index: 3291451 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8478. Min Act: -0.1700
Data Index: 1985448 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8166. Min Act: -0.1700
Data Index: 2510958 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8166. Min Act: -0.1700
Data Index: 8217390 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8478. Min Act: -0.1700
Data Index: 6906235 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8166. Min Act: -0.1700
Data Index: 1164008 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5353. Min Range: -6.5353
Max Act: 5.8166. Min Act: -0.1700
Data Index: 3767649 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19