Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.9546. Min Act: -0.1700
Data Index: 3854333 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.8296. Min Act: -0.1700
Data Index: 8415005 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.8296. Min Act: -0.1700
Data Index: 2171026 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.7359. Min Act: -0.1700
Data Index: 7745577 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.7046. Min Act: -0.1700
Data Index: 6881910 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.6734. Min Act: -0.1700
Data Index: 7840213 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.6421. Min Act: -0.1700
Data Index: 5418995 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.6109. Min Act: -0.1700
Data Index: 2595148 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.6109. Min Act: -0.1700
Data Index: 7013415 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.6109. Min Act: -0.1700
Data Index: 8197091 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.5796. Min Act: -0.1700
Data Index: 134460 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.5796. Min Act: -0.1700
Data Index: 5297906 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.5796. Min Act: -0.1700
Data Index: 4365935 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.5484. Min Act: -0.1700
Data Index: 829733 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.5484. Min Act: -0.1700
Data Index: 7750241 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.5171. Min Act: -0.1700
Data Index: 7747893 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.5171. Min Act: -0.1700
Data Index: 4140280 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.4859. Min Act: -0.1700
Data Index: 6878917 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.5484. Min Act: -0.1700
Data Index: 7140339 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9546. Min Range: -6.9546
Max Act: 6.4859. Min Act: -0.1700
Data Index: 4542229 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19