Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3459 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1857. Min Range: -6.1857
Max Act: 6.1857. Min Act: -0.1700
Data Index: 3544892 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.9669. Min Act: -0.1700
Data Index: 854300 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.8732. Min Act: -0.1700
Data Index: 7919860 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.8732. Min Act: -0.1700
Data Index: 7978368 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.8419. Min Act: -0.1700
Data Index: 7912992 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.8419. Min Act: -0.1700
Data Index: 1612929 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.8419. Min Act: -0.1700
Data Index: 7696565 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.8107. Min Act: -0.1700
Data Index: 4067358 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.7482. Min Act: -0.1700
Data Index: 3319681 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.7482. Min Act: -0.1700
Data Index: 861107 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.6857. Min Act: -0.1700
Data Index: 7472277 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.6544. Min Act: -0.1700
Data Index: 7613923 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.6544. Min Act: -0.1700
Data Index: 6669887 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.6232. Min Act: -0.1700
Data Index: 4615005 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.5607. Min Act: -0.1700
Data Index: 4921751 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.5919. Min Act: -0.1700
Data Index: 6780387 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.5607. Min Act: -0.1700
Data Index: 7160282 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.4982. Min Act: -0.1700
Data Index: 2601253 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.4982. Min Act: -0.1700
Data Index: 4921959 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1857. Min Range: -6.1857
Max Act: 5.4982. Min Act: -0.1700
Data Index: 3775076 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19