Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3420. Min Range: -6.3420
Max Act: 6.3420. Min Act: -0.1700
Data Index: 2713864 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3420. Min Range: -6.3420
Max Act: 6.0608. Min Act: -0.1700
Data Index: 1033842 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.9983. Min Act: -0.1700
Data Index: 6361208 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.9670. Min Act: -0.1700
Data Index: 5537479 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.9045. Min Act: -0.1700
Data Index: 4017014 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.8733. Min Act: -0.1700
Data Index: 2844048 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.8108. Min Act: -0.1700
Data Index: 5712231 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.8108. Min Act: -0.1700
Data Index: 8596674 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.8108. Min Act: -0.1700
Data Index: 7965952 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.7483. Min Act: -0.1700
Data Index: 2461042 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.7483. Min Act: -0.1700
Data Index: 58706 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.7170. Min Act: -0.1700
Data Index: 7566468 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.7170. Min Act: -0.1700
Data Index: 6293850 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.7170. Min Act: -0.1700
Data Index: 3229946 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.7170. Min Act: -0.1700
Data Index: 7482761 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.7170. Min Act: -0.1700
Data Index: 5680168 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.6858. Min Act: -0.1700
Data Index: 7651798 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.6858. Min Act: -0.1700
Data Index: 2985077 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.6858. Min Act: -0.1700
Data Index: 8191309 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3420. Min Range: -6.3420
Max Act: 5.6858. Min Act: -0.1700
Data Index: 2733769 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19