Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2414 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0239. Min Range: -9.0239
Max Act: 9.0239. Min Act: -0.1700
Data Index: 6122395 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.3989. Min Act: -0.1700
Data Index: 6862209 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.3989. Min Act: -0.1700
Data Index: 3575186 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.3989. Min Act: -0.1700
Data Index: 7457349 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.3364. Min Act: -0.1700
Data Index: 2163552 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.3364. Min Act: -0.1700
Data Index: 422609 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.3364. Min Act: -0.1700
Data Index: 3977536 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.2427. Min Act: -0.1700
Data Index: 7379446 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.2427. Min Act: -0.1700
Data Index: 4659660 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.2427. Min Act: -0.1700
Data Index: 4175477 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.2427. Min Act: -0.1700
Data Index: 5519633 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.1802. Min Act: -0.1700
Data Index: 6122396 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.2114. Min Act: -0.1700
Data Index: 1256070 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.1489. Min Act: -0.1700
Data Index: 3008851 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.1802. Min Act: -0.1700
Data Index: 3020663 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.0552. Min Act: -0.1700
Data Index: 4388485 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.0864. Min Act: -0.1700
Data Index: 4187457 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.0239. Min Act: -0.1700
Data Index: 871595 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0239. Min Range: -9.0239
Max Act: 7.9927. Min Act: -0.1700
Data Index: 6980778 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0239. Min Range: -9.0239
Max Act: 8.0239. Min Act: -0.1700
Data Index: 136170 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19