Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.9420. Min Act: -0.1700
Data Index: 6915081 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.7858. Min Act: -0.1700
Data Index: 6134618 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.5983. Min Act: -0.1700
Data Index: 2949300 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.5670. Min Act: -0.1700
Data Index: 363558 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.5358. Min Act: -0.1700
Data Index: 4230093 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.5358. Min Act: -0.1700
Data Index: 6762833 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.5045. Min Act: -0.1700
Data Index: 2800435 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.4733. Min Act: -0.1700
Data Index: 2399424 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.4733. Min Act: -0.1700
Data Index: 808856 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.4108. Min Act: -0.1700
Data Index: 542187 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.3795. Min Act: -0.1700
Data Index: 2243430 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.3795. Min Act: -0.1700
Data Index: 6047837 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.3795. Min Act: -0.1700
Data Index: 1144447 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.3483. Min Act: -0.1700
Data Index: 4547613 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.3483. Min Act: -0.1700
Data Index: 2498869 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.3483. Min Act: -0.1700
Data Index: 5081851 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.3483. Min Act: -0.1700
Data Index: 8459360 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.3170. Min Act: -0.1700
Data Index: 1608844 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.2858. Min Act: -0.1700
Data Index: 2244753 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9420. Min Range: -6.9420
Max Act: 6.2858. Min Act: -0.1700
Data Index: 3116619 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19