Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.5981. Min Act: -0.1700
Data Index: 7184110 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.5981. Min Act: -0.1700
Data Index: 2671872 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.5356. Min Act: -0.1700
Data Index: 7741919 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.5356. Min Act: -0.1700
Data Index: 2258419 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.4106. Min Act: -0.1700
Data Index: 3079223 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.2231. Min Act: -0.1700
Data Index: 6933490 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.2231. Min Act: -0.1700
Data Index: 1844150 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.2231. Min Act: -0.1700
Data Index: 2211340 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.1606. Min Act: -0.1700
Data Index: 3740632 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.1606. Min Act: -0.1700
Data Index: 5999265 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.1606. Min Act: -0.1700
Data Index: 8776188 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.1606. Min Act: -0.1700
Data Index: 5423070 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.0356. Min Act: -0.1700
Data Index: 5478340 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.0356. Min Act: -0.1700
Data Index: 270981 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.0356. Min Act: -0.1700
Data Index: 8223036 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.0356. Min Act: -0.1700
Data Index: 1517058 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5981. Min Range: -8.5981
Max Act: 8.0356. Min Act: -0.1700
Data Index: 6370379 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5981. Min Range: -8.5981
Max Act: 7.9731. Min Act: -0.1700
Data Index: 3518532 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5981. Min Range: -8.5981
Max Act: 7.9106. Min Act: -0.1700
Data Index: 3200291 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5981. Min Range: -8.5981
Max Act: 7.9106. Min Act: -0.1700
Data Index: 6059462 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19