Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.2707. Min Act: -0.1700
Data Index: 136613 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.3019. Min Act: -0.1700
Data Index: 6652213 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.3019. Min Act: -0.1700
Data Index: 1374272 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.2707. Min Act: -0.1700
Data Index: 2882048 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.2707. Min Act: -0.1700
Data Index: 256559 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.2394. Min Act: -0.1700
Data Index: 6191310 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.2394. Min Act: -0.1700
Data Index: 2236090 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.2394. Min Act: -0.1700
Data Index: 5555931 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.1769. Min Act: -0.1700
Data Index: 4825122 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.2082. Min Act: -0.1700
Data Index: 8167654 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.1769. Min Act: -0.1700
Data Index: 8477676 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.1457. Min Act: -0.1700
Data Index: 8293661 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.1457. Min Act: -0.1700
Data Index: 6691932 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.1457. Min Act: -0.1700
Data Index: 2882046 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.0832. Min Act: -0.1700
Data Index: 4490683 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.1144. Min Act: -0.1700
Data Index: 2416498 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.0519. Min Act: -0.1700
Data Index: 1413202 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.0832. Min Act: -0.1700
Data Index: 4104887 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.0832. Min Act: -0.1700
Data Index: 694809 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3019. Min Range: -7.3019
Max Act: 7.0832. Min Act: -0.1700
Data Index: 6844320 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19