Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1410 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.7932. Min Act: -0.1700
Data Index: 1394970 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.3557. Min Act: -0.1700
Data Index: 2279325 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.2932. Min Act: -0.1700
Data Index: 4663767 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.0432. Min Act: -0.1700
Data Index: 6518626 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7932. Min Range: -9.7932
Max Act: 9.0432. Min Act: -0.1700
Data Index: 4115594 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.9182. Min Act: -0.1700
Data Index: 598679 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.8557. Min Act: -0.1700
Data Index: 2555967 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.8557. Min Act: -0.1700
Data Index: 721615 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.8557. Min Act: -0.1700
Data Index: 6323258 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.8557. Min Act: -0.1700
Data Index: 2237328 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.7932. Min Act: -0.1700
Data Index: 4497046 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.7932. Min Act: -0.1700
Data Index: 6816265 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.7307. Min Act: -0.1700
Data Index: 6492026 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.7307. Min Act: -0.1700
Data Index: 4603275 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.7307. Min Act: -0.1700
Data Index: 123410 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.7307. Min Act: -0.1700
Data Index: 8110102 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.7307. Min Act: -0.1700
Data Index: 306323 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.6682. Min Act: -0.1700
Data Index: 2156101 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.7307. Min Act: -0.1700
Data Index: 1394967 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7932. Min Range: -9.7932
Max Act: 8.6682. Min Act: -0.1700
Data Index: 2195999 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19