Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 470 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0302. Min Range: -5.0302
Max Act: 5.0302. Min Act: -0.1700
Data Index: 4958706 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0302. Min Range: -5.0302
Max Act: 5.0302. Min Act: -0.1700
Data Index: 7706947 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9365. Min Act: -0.1700
Data Index: 7364287 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9990. Min Act: -0.1700
Data Index: 901469 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9677. Min Act: -0.1700
Data Index: 7101899 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.9052. Min Act: -0.1700
Data Index: 6186100 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8740. Min Act: -0.1700
Data Index: 5675358 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8427. Min Act: -0.1700
Data Index: 4415338 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8427. Min Act: -0.1700
Data Index: 1104966 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8115. Min Act: -0.1700
Data Index: 1170936 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8115. Min Act: -0.1700
Data Index: 3861125 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8115. Min Act: -0.1700
Data Index: 4115072 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8115. Min Act: -0.1700
Data Index: 8113416 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8115. Min Act: -0.1700
Data Index: 2037523 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8115. Min Act: -0.1700
Data Index: 772044 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8115. Min Act: -0.1700
Data Index: 3120259 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.8115. Min Act: -0.1700
Data Index: 3203899 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.7802. Min Act: -0.1700
Data Index: 1835334 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.7490. Min Act: -0.1700
Data Index: 7901362 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0302. Min Range: -5.0302
Max Act: 4.7490. Min Act: -0.1700
Data Index: 2131971 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19