Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 348 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1231. Min Range: -5.1231
Max Act: 5.1231. Min Act: -0.1700
Data Index: 6058876 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1231. Min Range: -5.1231
Max Act: 5.0606. Min Act: -0.1700
Data Index: 298242 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.9668. Min Act: -0.1700
Data Index: 5996246 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.9668. Min Act: -0.1700
Data Index: 3284332 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.9043. Min Act: -0.1700
Data Index: 6603894 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.8731. Min Act: -0.1700
Data Index: 7664792 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.8418. Min Act: -0.1700
Data Index: 4225025 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.8106. Min Act: -0.1700
Data Index: 6058871 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.8106. Min Act: -0.1700
Data Index: 2580863 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7793. Min Act: -0.1700
Data Index: 3459493 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7793. Min Act: -0.1700
Data Index: 3090076 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7793. Min Act: -0.1700
Data Index: 5422004 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7481. Min Act: -0.1700
Data Index: 5402157 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7481. Min Act: -0.1700
Data Index: 4225026 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7481. Min Act: -0.1700
Data Index: 440171 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7168. Min Act: -0.1700
Data Index: 3498362 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7168. Min Act: -0.1700
Data Index: 6058873 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7481. Min Act: -0.1700
Data Index: 2774931 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7168. Min Act: -0.1700
Data Index: 8312358 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1231. Min Range: -5.1231
Max Act: 4.7168. Min Act: -0.1700
Data Index: 8797097 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19