Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4688 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.6412. Min Act: -0.1700
Data Index: 1493722 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5787. Min Act: -0.1700
Data Index: 2833609 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.6100. Min Act: -0.1700
Data Index: 3595466 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5787. Min Act: -0.1700
Data Index: 7284271 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5787. Min Act: -0.1700
Data Index: 8063512 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5787. Min Act: -0.1700
Data Index: 350465 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5475. Min Act: -0.1700
Data Index: 4792649 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5475. Min Act: -0.1700
Data Index: 7625960 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5475. Min Act: -0.1700
Data Index: 549000 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5162. Min Act: -0.1700
Data Index: 2598875 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5475. Min Act: -0.1700
Data Index: 1803979 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4850. Min Act: -0.1700
Data Index: 8310254 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5162. Min Act: -0.1700
Data Index: 2379368 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4850. Min Act: -0.1700
Data Index: 4415650 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4850. Min Act: -0.1700
Data Index: 2203366 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4850. Min Act: -0.1700
Data Index: 5750463 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4850. Min Act: -0.1700
Data Index: 7382741 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4537. Min Act: -0.1700
Data Index: 1764413 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4537. Min Act: -0.1700
Data Index: 4968243 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4537. Min Act: -0.1700
Data Index: 791881 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19