Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1067 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.4724. Min Act: -0.1700
Data Index: 1769627 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.4724. Min Act: -0.1700
Data Index: 7564830 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.4724. Min Act: -0.1700
Data Index: 1839492 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.4412. Min Act: -0.1700
Data Index: 1826123 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.4099. Min Act: -0.1700
Data Index: 4570654 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.4099. Min Act: -0.1700
Data Index: 4552447 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.3474. Min Act: -0.1700
Data Index: 7553019 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.3474. Min Act: -0.1700
Data Index: 4162297 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.3474. Min Act: -0.1700
Data Index: 5475408 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.3162. Min Act: -0.1700
Data Index: 2517844 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.3162. Min Act: -0.1700
Data Index: 1883558 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.3162. Min Act: -0.1700
Data Index: 6142049 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.3162. Min Act: -0.1700
Data Index: 7952161 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.3162. Min Act: -0.1700
Data Index: 8762955 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.2849. Min Act: -0.1700
Data Index: 7280877 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.2849. Min Act: -0.1700
Data Index: 1839493 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.2849. Min Act: -0.1700
Data Index: 7444526 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.2849. Min Act: -0.1700
Data Index: 1263727 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.2537. Min Act: -0.1700
Data Index: 1357567 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4724. Min Range: -6.4724
Max Act: 6.2537. Min Act: -0.1700
Data Index: 307021 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19