Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.6927. Min Act: -0.1700
Data Index: 8643460 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.6927. Min Act: -0.1700
Data Index: 1207315 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.6302. Min Act: -0.1700
Data Index: 5157015 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.6615. Min Act: -0.1700
Data Index: 3013271 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.6302. Min Act: -0.1700
Data Index: 5295558 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.6302. Min Act: -0.1700
Data Index: 7787483 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5990. Min Act: -0.1700
Data Index: 4060429 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.6302. Min Act: -0.1700
Data Index: 5278557 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5990. Min Act: -0.1700
Data Index: 1127639 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5990. Min Act: -0.1700
Data Index: 3002413 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5990. Min Act: -0.1700
Data Index: 7929857 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5365. Min Act: -0.1700
Data Index: 3173903 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5677. Min Act: -0.1700
Data Index: 920948 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5052. Min Act: -0.1700
Data Index: 525807 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5365. Min Act: -0.1700
Data Index: 2851699 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5052. Min Act: -0.1700
Data Index: 989428 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5052. Min Act: -0.1700
Data Index: 2301207 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5052. Min Act: -0.1700
Data Index: 7130420 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5052. Min Act: -0.1700
Data Index: 6944909 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6927. Min Range: -4.6927
Max Act: 4.5052. Min Act: -0.1700
Data Index: 4279422 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19