Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2327 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0109. Min Range: -5.0109
Max Act: 5.0109. Min Act: -0.1700
Data Index: 5656497 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8546. Min Act: -0.1700
Data Index: 5811236 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8234. Min Act: -0.1700
Data Index: 3573695 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7296. Min Act: -0.1700
Data Index: 3494378 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7296. Min Act: -0.1700
Data Index: 6987809 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6671. Min Act: -0.1700
Data Index: 5385101 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6671. Min Act: -0.1700
Data Index: 7546367 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6046. Min Act: -0.1700
Data Index: 3028759 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6359. Min Act: -0.1700
Data Index: 1569850 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6359. Min Act: -0.1700
Data Index: 5917675 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6359. Min Act: -0.1700
Data Index: 4372836 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6359. Min Act: -0.1700
Data Index: 4412631 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6359. Min Act: -0.1700
Data Index: 6232514 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6671. Min Act: -0.1700
Data Index: 6555407 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.5734. Min Act: -0.1700
Data Index: 1312496 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6046. Min Act: -0.1700
Data Index: 8017637 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6046. Min Act: -0.1700
Data Index: 2823472 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6046. Min Act: -0.1700
Data Index: 6222086 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6046. Min Act: -0.1700
Data Index: 3506080 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6046. Min Act: -0.1700
Data Index: 2674035 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19