Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1147. Min Range: -5.1147
Max Act: 5.1147. Min Act: -0.1700
Data Index: 3922005 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.9584. Min Act: -0.1700
Data Index: 4031192 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.8959. Min Act: -0.1700
Data Index: 1551704 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.8959. Min Act: -0.1700
Data Index: 1256596 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.8022. Min Act: -0.1700
Data Index: 8795872 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7709. Min Act: -0.1700
Data Index: 757102 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7397. Min Act: -0.1700
Data Index: 2700168 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7397. Min Act: -0.1700
Data Index: 1556285 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7397. Min Act: -0.1700
Data Index: 4030190 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7084. Min Act: -0.1700
Data Index: 2254647 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7084. Min Act: -0.1700
Data Index: 3482748 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7084. Min Act: -0.1700
Data Index: 2957034 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7397. Min Act: -0.1700
Data Index: 2898434 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7084. Min Act: -0.1700
Data Index: 7655490 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7397. Min Act: -0.1700
Data Index: 2038936 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.7084. Min Act: -0.1700
Data Index: 3748094 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.6772. Min Act: -0.1700
Data Index: 827106 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.6772. Min Act: -0.1700
Data Index: 7651632 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.6772. Min Act: -0.1700
Data Index: 4997127 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1147. Min Range: -5.1147
Max Act: 4.6459. Min Act: -0.1700
Data Index: 1299660 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19