Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.7275. Min Act: -0.1700
Data Index: 518850 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.6650. Min Act: -0.1700
Data Index: 1289635 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.5087. Min Act: -0.1700
Data Index: 8597398 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.5087. Min Act: -0.1700
Data Index: 8410421 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.5087. Min Act: -0.1700
Data Index: 2197414 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.4150. Min Act: -0.1700
Data Index: 7437022 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.4775. Min Act: -0.1700
Data Index: 2215048 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.4150. Min Act: -0.1700
Data Index: 322652 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.2899. Min Act: -0.1700
Data Index: 3971797 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.2587. Min Act: -0.1700
Data Index: 94422 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.2274. Min Act: -0.1700
Data Index: 3186444 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.2274. Min Act: -0.1700
Data Index: 5686498 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.2274. Min Act: -0.1700
Data Index: 1214556 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.2274. Min Act: -0.1700
Data Index: 7130712 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.1962. Min Act: -0.1700
Data Index: 5314059 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.1649. Min Act: -0.1700
Data Index: 916976 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.1337. Min Act: -0.1700
Data Index: 1076908 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.1649. Min Act: -0.1700
Data Index: 8305165 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.1649. Min Act: -0.1700
Data Index: 237586 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7275. Min Range: -4.7275
Max Act: 4.1337. Min Act: -0.1700
Data Index: 5944905 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19