Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 8790191 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1366. Min Act: -0.1700
Data Index: 1100240 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.0428. Min Act: -0.1700
Data Index: 1435344 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.0428. Min Act: -0.1700
Data Index: 2364556 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.0428. Min Act: -0.1700
Data Index: 3625044 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.0116. Min Act: -0.1700
Data Index: 336330 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.9803. Min Act: -0.1700
Data Index: 8425170 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.9803. Min Act: -0.1700
Data Index: 2506080 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.9803. Min Act: -0.1700
Data Index: 2764925 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.9178. Min Act: -0.1700
Data Index: 2271833 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.9178. Min Act: -0.1700
Data Index: 494390 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.8866. Min Act: -0.1700
Data Index: 7489929 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.8866. Min Act: -0.1700
Data Index: 5748382 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.9178. Min Act: -0.1700
Data Index: 7954833 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.8866. Min Act: -0.1700
Data Index: 2853586 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.8866. Min Act: -0.1700
Data Index: 7634155 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 7698542 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 1566973 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.8553. Min Act: -0.1700
Data Index: 347251 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5428. Min Range: -5.5428
Max Act: 4.8241. Min Act: -0.1700
Data Index: 1601275 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19