Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.6471. Min Act: -0.1700
Data Index: 2733178 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.5533. Min Act: -0.1700
Data Index: 6979331 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.5533. Min Act: -0.1700
Data Index: 3172882 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4364555 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.3658. Min Act: -0.1700
Data Index: 7176494 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.3346. Min Act: -0.1700
Data Index: 5893721 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.3346. Min Act: -0.1700
Data Index: 2008475 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.3346. Min Act: -0.1700
Data Index: 5293279 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.3033. Min Act: -0.1700
Data Index: 27018 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2721. Min Act: -0.1700
Data Index: 726841 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.3033. Min Act: -0.1700
Data Index: 5660243 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.3033. Min Act: -0.1700
Data Index: 3911561 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2721. Min Act: -0.1700
Data Index: 5939357 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2721. Min Act: -0.1700
Data Index: 1785981 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2721. Min Act: -0.1700
Data Index: 6534491 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2408. Min Act: -0.1700
Data Index: 8388130 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2408. Min Act: -0.1700
Data Index: 1664317 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2095. Min Act: -0.1700
Data Index: 4301337 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2408. Min Act: -0.1700
Data Index: 1773523 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6471. Min Range: -4.6471
Max Act: 4.2095. Min Act: -0.1700
Data Index: 5896964 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19