Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6302. Min Range: -6.6302
Max Act: 6.6302. Min Act: -0.1700
Data Index: 6229319 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.9739. Min Act: -0.1700
Data Index: 3289081 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.7552. Min Act: -0.1700
Data Index: 2531641 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.7239. Min Act: -0.1700
Data Index: 2379511 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.7239. Min Act: -0.1700
Data Index: 4911011 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.6614. Min Act: -0.1700
Data Index: 620241 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.6614. Min Act: -0.1700
Data Index: 8537705 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.5989. Min Act: -0.1700
Data Index: 8395384 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.5677. Min Act: -0.1700
Data Index: 1507988 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.5677. Min Act: -0.1700
Data Index: 6113465 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.5677. Min Act: -0.1700
Data Index: 3906186 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.5364. Min Act: -0.1700
Data Index: 3876685 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.5364. Min Act: -0.1700
Data Index: 128125 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.4739. Min Act: -0.1700
Data Index: 1964421 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.4739. Min Act: -0.1700
Data Index: 2379514 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.4427. Min Act: -0.1700
Data Index: 4866000 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.4427. Min Act: -0.1700
Data Index: 1508010 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.4427. Min Act: -0.1700
Data Index: 1035457 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.3802. Min Act: -0.1700
Data Index: 2538268 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6302. Min Range: -6.6302
Max Act: 5.3802. Min Act: -0.1700
Data Index: 6268744 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19