Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1013 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.9601. Min Act: -0.1700
Data Index: 7237995 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.9601. Min Act: -0.1700
Data Index: 704570 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.9289. Min Act: -0.1700
Data Index: 6134846 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.8976. Min Act: -0.1700
Data Index: 8215897 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.8664. Min Act: -0.1700
Data Index: 1460180 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.8039. Min Act: -0.1700
Data Index: 2155338 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.8039. Min Act: -0.1700
Data Index: 832270 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7726. Min Act: -0.1700
Data Index: 5997095 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7726. Min Act: -0.1700
Data Index: 84720 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7726. Min Act: -0.1700
Data Index: 4346896 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7726. Min Act: -0.1700
Data Index: 8812794 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7726. Min Act: -0.1700
Data Index: 7822377 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7726. Min Act: -0.1700
Data Index: 5187695 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7414. Min Act: -0.1700
Data Index: 1876519 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7414. Min Act: -0.1700
Data Index: 6442415 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7414. Min Act: -0.1700
Data Index: 1981441 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.6789. Min Act: -0.1700
Data Index: 6134845 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.7101. Min Act: -0.1700
Data Index: 5996040 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.6789. Min Act: -0.1700
Data Index: 120 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9601. Min Range: -5.9601
Max Act: 5.6789. Min Act: -0.1700
Data Index: 5837734 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19