Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1507. Min Range: -6.1507
Max Act: 6.1507. Min Act: -0.1700
Data Index: 357172 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1507. Min Range: -6.1507
Max Act: 6.0882. Min Act: -0.1700
Data Index: 7909147 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1507. Min Range: -6.1507
Max Act: 6.0569. Min Act: -0.1700
Data Index: 3686175 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.9319. Min Act: -0.1700
Data Index: 721387 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.9319. Min Act: -0.1700
Data Index: 4170623 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.9007. Min Act: -0.1700
Data Index: 6343369 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.9319. Min Act: -0.1700
Data Index: 7362232 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1084227 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.8694. Min Act: -0.1700
Data Index: 4676708 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.8694. Min Act: -0.1700
Data Index: 4914176 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.8694. Min Act: -0.1700
Data Index: 4520264 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.8694. Min Act: -0.1700
Data Index: 3560643 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.8069. Min Act: -0.1700
Data Index: 5243731 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.7757. Min Act: -0.1700
Data Index: 5915292 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.7444. Min Act: -0.1700
Data Index: 4914171 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.7132. Min Act: -0.1700
Data Index: 8303669 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.7444. Min Act: -0.1700
Data Index: 436287 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.7444. Min Act: -0.1700
Data Index: 5904012 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.7132. Min Act: -0.1700
Data Index: 6154224 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1507. Min Range: -6.1507
Max Act: 5.7132. Min Act: -0.1700
Data Index: 2317766 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19