Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1431. Min Range: -6.1431
Max Act: 6.1431. Min Act: -0.1700
Data Index: 8764821 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.9556. Min Act: -0.1700
Data Index: 5300287 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.9868. Min Act: -0.1700
Data Index: 5273976 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.9556. Min Act: -0.1700
Data Index: 5735047 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.9556. Min Act: -0.1700
Data Index: 5735048 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.9243. Min Act: -0.1700
Data Index: 4864302 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.9243. Min Act: -0.1700
Data Index: 5394125 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.7993. Min Act: -0.1700
Data Index: 1138543 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.6743. Min Act: -0.1700
Data Index: 7282871 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.6431. Min Act: -0.1700
Data Index: 5567346 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.6743. Min Act: -0.1700
Data Index: 831181 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.7056. Min Act: -0.1700
Data Index: 12484 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.6118. Min Act: -0.1700
Data Index: 1368493 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.6118. Min Act: -0.1700
Data Index: 998885 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.6118. Min Act: -0.1700
Data Index: 5619869 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.5806. Min Act: -0.1700
Data Index: 5170508 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.5806. Min Act: -0.1700
Data Index: 7416138 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.5181. Min Act: -0.1700
Data Index: 6422706 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.5181. Min Act: -0.1700
Data Index: 4731723 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1431. Min Range: -6.1431
Max Act: 5.5493. Min Act: -0.1700
Data Index: 4493694 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19