Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0246. Min Range: -7.0246
Max Act: 7.0246. Min Act: -0.1700
Data Index: 5516409 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.7121. Min Act: -0.1700
Data Index: 1753437 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.6808. Min Act: -0.1700
Data Index: 3339886 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.6183. Min Act: -0.1700
Data Index: 4191205 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.5871. Min Act: -0.1700
Data Index: 4928974 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.5871. Min Act: -0.1700
Data Index: 1019406 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.4308. Min Act: -0.1700
Data Index: 5625776 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.4621. Min Act: -0.1700
Data Index: 5483613 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.4621. Min Act: -0.1700
Data Index: 3565153 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.4621. Min Act: -0.1700
Data Index: 6583870 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.4308. Min Act: -0.1700
Data Index: 4718964 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.4308. Min Act: -0.1700
Data Index: 2653284 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.3996. Min Act: -0.1700
Data Index: 8596843 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.3996. Min Act: -0.1700
Data Index: 8227637 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.3996. Min Act: -0.1700
Data Index: 5778662 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.3996. Min Act: -0.1700
Data Index: 3344453 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.4308. Min Act: -0.1700
Data Index: 3862457 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.3371. Min Act: -0.1700
Data Index: 3237073 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.3683. Min Act: -0.1700
Data Index: 7179680 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0246. Min Range: -7.0246
Max Act: 6.3371. Min Act: -0.1700
Data Index: 3003684 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19