Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.3670. Min Act: -0.1700
Data Index: 8818605 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.3670. Min Act: -0.1700
Data Index: 812450 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.3358. Min Act: -0.1700
Data Index: 4975006 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.2420. Min Act: -0.1700
Data Index: 7871321 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.2420. Min Act: -0.1700
Data Index: 7107091 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1795. Min Act: -0.1700
Data Index: 1190528 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1483. Min Act: -0.1700
Data Index: 3621985 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1483. Min Act: -0.1700
Data Index: 2268546 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1483. Min Act: -0.1700
Data Index: 1842778 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1483. Min Act: -0.1700
Data Index: 5097314 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1170. Min Act: -0.1700
Data Index: 6707856 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1170. Min Act: -0.1700
Data Index: 2615610 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.1170. Min Act: -0.1700
Data Index: 2213729 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0858. Min Act: -0.1700
Data Index: 3015120 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0858. Min Act: -0.1700
Data Index: 6877546 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0858. Min Act: -0.1700
Data Index: 519279 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0858. Min Act: -0.1700
Data Index: 2072200 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0545. Min Act: -0.1700
Data Index: 3796514 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0545. Min Act: -0.1700
Data Index: 2879471 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3670. Min Range: -6.3670
Max Act: 6.0233. Min Act: -0.1700
Data Index: 1372598 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19