Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 833 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.7086. Min Act: -0.1700
Data Index: 4765946 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.5836. Min Act: -0.1700
Data Index: 412230 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.5523. Min Act: -0.1700
Data Index: 5443529 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.5523. Min Act: -0.1700
Data Index: 5056591 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.5523. Min Act: -0.1700
Data Index: 8733981 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4898. Min Act: -0.1700
Data Index: 7412945 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.5210. Min Act: -0.1700
Data Index: 3245923 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4898. Min Act: -0.1700
Data Index: 5115073 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.5210. Min Act: -0.1700
Data Index: 350556 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4273. Min Act: -0.1700
Data Index: 5076506 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4898. Min Act: -0.1700
Data Index: 7212671 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4273. Min Act: -0.1700
Data Index: 5075876 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4898. Min Act: -0.1700
Data Index: 4658150 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4585. Min Act: -0.1700
Data Index: 4627205 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4585. Min Act: -0.1700
Data Index: 8302752 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4585. Min Act: -0.1700
Data Index: 7072550 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4273. Min Act: -0.1700
Data Index: 3925708 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4585. Min Act: -0.1700
Data Index: 3947592 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4273. Min Act: -0.1700
Data Index: 5140563 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7086. Min Range: -4.7086
Max Act: 4.4273. Min Act: -0.1700
Data Index: 2482460 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19