Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2450 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.3380. Min Act: -0.1700
Data Index: 5832063 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.3068. Min Act: -0.1700
Data Index: 2922309 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.2755. Min Act: -0.1700
Data Index: 7238578 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.3068. Min Act: -0.1700
Data Index: 4847725 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.2130. Min Act: -0.1700
Data Index: 475426 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.2130. Min Act: -0.1700
Data Index: 3210723 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1505. Min Act: -0.1700
Data Index: 781584 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1818. Min Act: -0.1700
Data Index: 2526398 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1818. Min Act: -0.1700
Data Index: 1507437 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1818. Min Act: -0.1700
Data Index: 1656294 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1505. Min Act: -0.1700
Data Index: 7797689 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1505. Min Act: -0.1700
Data Index: 1708553 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1505. Min Act: -0.1700
Data Index: 3518391 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1192. Min Act: -0.1700
Data Index: 3421074 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1505. Min Act: -0.1700
Data Index: 1844125 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1192. Min Act: -0.1700
Data Index: 7114549 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1505. Min Act: -0.1700
Data Index: 2446236 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.1192. Min Act: -0.1700
Data Index: 5803735 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.0880. Min Act: -0.1700
Data Index: 2089482 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3380. Min Range: -4.3380
Max Act: 4.0567. Min Act: -0.1700
Data Index: 2138221 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19