Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2182 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.7147. Min Act: -0.1700
Data Index: 2394122 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.6522. Min Act: -0.1700
Data Index: 756281 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.6522. Min Act: -0.1700
Data Index: 7254668 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.5585. Min Act: -0.1700
Data Index: 1286461 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.5585. Min Act: -0.1700
Data Index: 7248587 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.4960. Min Act: -0.1700
Data Index: 8648023 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.4647. Min Act: -0.1700
Data Index: 709121 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.4335. Min Act: -0.1700
Data Index: 5745067 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.4647. Min Act: -0.1700
Data Index: 755606 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.4647. Min Act: -0.1700
Data Index: 8457907 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.3710. Min Act: -0.1700
Data Index: 6894580 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.4022. Min Act: -0.1700
Data Index: 1485316 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.4335. Min Act: -0.1700
Data Index: 8285802 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.3397. Min Act: -0.1700
Data Index: 7295140 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.3397. Min Act: -0.1700
Data Index: 2017793 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.2772. Min Act: -0.1700
Data Index: 7133608 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.3085. Min Act: -0.1700
Data Index: 7016213 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.3085. Min Act: -0.1700
Data Index: 7495531 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.3085. Min Act: -0.1700
Data Index: 2043311 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7147. Min Range: -6.7147
Max Act: 6.2772. Min Act: -0.1700
Data Index: 6395130 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19