Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.3208. Min Act: -0.1700
Data Index: 4072679 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.2270. Min Act: -0.1700
Data Index: 765134 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.1645. Min Act: -0.1700
Data Index: 8025192 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.1333. Min Act: -0.1700
Data Index: 448752 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.1333. Min Act: -0.1700
Data Index: 6447409 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0708. Min Act: -0.1700
Data Index: 3663274 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0395. Min Act: -0.1700
Data Index: 2121098 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0708. Min Act: -0.1700
Data Index: 3817757 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0395. Min Act: -0.1700
Data Index: 8081453 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0395. Min Act: -0.1700
Data Index: 411820 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0395. Min Act: -0.1700
Data Index: 5582987 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0395. Min Act: -0.1700
Data Index: 8012752 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0395. Min Act: -0.1700
Data Index: 1915765 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0395. Min Act: -0.1700
Data Index: 4629183 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0395. Min Act: -0.1700
Data Index: 6360709 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0083. Min Act: -0.1700
Data Index: 6694156 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0083. Min Act: -0.1700
Data Index: 951905 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3208. Min Range: -5.3208
Max Act: 5.0083. Min Act: -0.1700
Data Index: 5740503 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3208. Min Range: -5.3208
Max Act: 4.9770. Min Act: -0.1700
Data Index: 672891 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3208. Min Range: -5.3208
Max Act: 4.9770. Min Act: -0.1700
Data Index: 603874 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19