Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.6144. Min Act: -0.1700
Data Index: 7335104 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.4894. Min Act: -0.1700
Data Index: 4794287 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.3644. Min Act: -0.1700
Data Index: 5863228 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.3644. Min Act: -0.1700
Data Index: 46214 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.3019. Min Act: -0.1700
Data Index: 3647337 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.2394. Min Act: -0.1700
Data Index: 3452671 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.1144. Min Act: -0.1700
Data Index: 3309894 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.1144. Min Act: -0.1700
Data Index: 6525358 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.1144. Min Act: -0.1700
Data Index: 7767314 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.1144. Min Act: -0.1700
Data Index: 6136706 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.1144. Min Act: -0.1700
Data Index: 5627533 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.1144. Min Act: -0.1700
Data Index: 7519234 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.0519. Min Act: -0.1700
Data Index: 1002484 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.0519. Min Act: -0.1700
Data Index: 6200630 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.1144. Min Act: -0.1700
Data Index: 3921885 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.0519. Min Act: -0.1700
Data Index: 809239 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6144. Min Range: -9.6144
Max Act: 9.0519. Min Act: -0.1700
Data Index: 6685344 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6144. Min Range: -9.6144
Max Act: 8.9894. Min Act: -0.1700
Data Index: 7088518 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6144. Min Range: -9.6144
Max Act: 8.9894. Min Act: -0.1700
Data Index: 6456060 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6144. Min Range: -9.6144
Max Act: 8.9894. Min Act: -0.1700
Data Index: 3540807 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19