Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4524 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.7395. Min Act: -0.1700
Data Index: 6453250 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.7083. Min Act: -0.1700
Data Index: 2296702 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.7083. Min Act: -0.1700
Data Index: 1676705 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6770. Min Act: -0.1700
Data Index: 5434032 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6770. Min Act: -0.1700
Data Index: 6917859 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6458. Min Act: -0.1700
Data Index: 3094833 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6458. Min Act: -0.1700
Data Index: 3099358 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6458. Min Act: -0.1700
Data Index: 6453253 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6458. Min Act: -0.1700
Data Index: 5443600 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6458. Min Act: -0.1700
Data Index: 1676708 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6770. Min Act: -0.1700
Data Index: 6360731 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6458. Min Act: -0.1700
Data Index: 1867570 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6458. Min Act: -0.1700
Data Index: 2215177 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 373465 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 373454 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 8367963 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 6917863 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 3094835 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 5153871 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7395. Min Range: -5.7395
Max Act: 5.6145. Min Act: -0.1700
Data Index: 4599574 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19