Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1019 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.7889. Min Act: -0.1700
Data Index: 5998180 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.7107. Min Act: -0.1700
Data Index: 838490 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6794. Min Act: -0.1700
Data Index: 113865 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6794. Min Act: -0.1700
Data Index: 3057461 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6325. Min Act: -0.1700
Data Index: 5137369 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6325. Min Act: -0.1700
Data Index: 6109696 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6481. Min Act: -0.1700
Data Index: 5541396 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6168. Min Act: -0.1700
Data Index: 7105163 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6325. Min Act: -0.1700
Data Index: 6767793 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6012. Min Act: -0.1700
Data Index: 7772276 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5855. Min Act: -0.1700
Data Index: 5729975 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6168. Min Act: -0.1700
Data Index: 8622761 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5855. Min Act: -0.1700
Data Index: 6138446 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6012. Min Act: -0.1700
Data Index: 1441941 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.6012. Min Act: -0.1700
Data Index: 7319347 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5699. Min Act: -0.1700
Data Index: 4428797 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5542. Min Act: -0.1700
Data Index: 3866321 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5386. Min Act: -0.1700
Data Index: 4238784 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5386. Min Act: -0.1700
Data Index: 2082457 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7889. Min Range: -3.7889
Max Act: 3.5542. Min Act: -0.1700
Data Index: 157980 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19