Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 678 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.5343. Min Act: -0.1700
Data Index: 3333738 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.4093. Min Act: -0.1700
Data Index: 798183 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.3781. Min Act: -0.1700
Data Index: 5835922 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.3468. Min Act: -0.1700
Data Index: 5933826 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.3156. Min Act: -0.1700
Data Index: 7260281 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.3468. Min Act: -0.1700
Data Index: 7081754 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.2531. Min Act: -0.1700
Data Index: 3216197 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.2531. Min Act: -0.1700
Data Index: 3438344 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.2531. Min Act: -0.1700
Data Index: 8778166 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.2218. Min Act: -0.1700
Data Index: 4528010 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.1906. Min Act: -0.1700
Data Index: 6199475 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.1906. Min Act: -0.1700
Data Index: 312620 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.1906. Min Act: -0.1700
Data Index: 3615001 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.1593. Min Act: -0.1700
Data Index: 6305554 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.1281. Min Act: -0.1700
Data Index: 8218268 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.1906. Min Act: -0.1700
Data Index: 4863039 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.1281. Min Act: -0.1700
Data Index: 3900800 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.1281. Min Act: -0.1700
Data Index: 3002667 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.0968. Min Act: -0.1700
Data Index: 1672237 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5343. Min Range: -5.5343
Max Act: 5.0968. Min Act: -0.1700
Data Index: 7887092 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19