Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.9657. Min Act: -0.1700
Data Index: 3998419 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.8407. Min Act: -0.1700
Data Index: 881187 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.8094. Min Act: -0.1700
Data Index: 3410024 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.8094. Min Act: -0.1700
Data Index: 5099325 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.7781. Min Act: -0.1700
Data Index: 1904891 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.7156. Min Act: -0.1700
Data Index: 2791328 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.7156. Min Act: -0.1700
Data Index: 3230963 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6999. Min Act: -0.1700
Data Index: 6719127 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6999. Min Act: -0.1700
Data Index: 639381 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6686. Min Act: -0.1700
Data Index: 4783933 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6530. Min Act: -0.1700
Data Index: 1939328 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6530. Min Act: -0.1700
Data Index: 471053 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6373. Min Act: -0.1700
Data Index: 5395596 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6373. Min Act: -0.1700
Data Index: 3322850 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6373. Min Act: -0.1700
Data Index: 3505630 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6217. Min Act: -0.1700
Data Index: 7033649 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6373. Min Act: -0.1700
Data Index: 7972516 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6217. Min Act: -0.1700
Data Index: 2728651 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6217. Min Act: -0.1700
Data Index: 5102642 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9657. Min Range: -3.9657
Max Act: 3.6060. Min Act: -0.1700
Data Index: 6566446 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19