Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3429. Min Range: -7.3429
Max Act: 7.3429. Min Act: -0.1700
Data Index: 36069 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3429. Min Range: -7.3429
Max Act: 7.3429. Min Act: -0.1700
Data Index: 502675 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3429. Min Range: -7.3429
Max Act: 7.0304. Min Act: -0.1700
Data Index: 6117245 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3429. Min Range: -7.3429
Max Act: 7.0616. Min Act: -0.1700
Data Index: 3152180 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.9679. Min Act: -0.1700
Data Index: 5924286 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.9366. Min Act: -0.1700
Data Index: 334551 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.9054. Min Act: -0.1700
Data Index: 7102288 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.8429. Min Act: -0.1700
Data Index: 2978350 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.8741. Min Act: -0.1700
Data Index: 367077 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.8741. Min Act: -0.1700
Data Index: 7996892 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.8429. Min Act: -0.1700
Data Index: 5421127 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.8429. Min Act: -0.1700
Data Index: 3704988 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.7804. Min Act: -0.1700
Data Index: 6961023 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.7804. Min Act: -0.1700
Data Index: 8051991 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.8116. Min Act: -0.1700
Data Index: 2067905 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.7804. Min Act: -0.1700
Data Index: 6693419 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.7491. Min Act: -0.1700
Data Index: 6086974 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.7491. Min Act: -0.1700
Data Index: 8632114 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.7179. Min Act: -0.1700
Data Index: 6797640 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3429. Min Range: -7.3429
Max Act: 6.7491. Min Act: -0.1700
Data Index: 899999 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19