Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.6231. Min Act: -0.1700
Data Index: 5931382 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4668. Min Act: -0.1700
Data Index: 3949472 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4356. Min Act: -0.1700
Data Index: 5931381 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.4043. Min Act: -0.1700
Data Index: 6154755 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.3418. Min Act: -0.1700
Data Index: 7372327 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.3106. Min Act: -0.1700
Data Index: 8388842 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.3106. Min Act: -0.1700
Data Index: 2614905 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.2481. Min Act: -0.1700
Data Index: 4205390 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.2168. Min Act: -0.1700
Data Index: 218748 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.2168. Min Act: -0.1700
Data Index: 1738138 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1856. Min Act: -0.1700
Data Index: 3895666 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1856. Min Act: -0.1700
Data Index: 1045860 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1856. Min Act: -0.1700
Data Index: 825806 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1856. Min Act: -0.1700
Data Index: 2088045 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1856. Min Act: -0.1700
Data Index: 7590820 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.2168. Min Act: -0.1700
Data Index: 3343262 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1543. Min Act: -0.1700
Data Index: 7851012 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1231. Min Act: -0.1700
Data Index: 7469073 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1543. Min Act: -0.1700
Data Index: 1559317 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6231. Min Range: -4.6231
Max Act: 4.1856. Min Act: -0.1700
Data Index: 7909484 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19