Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.4428. Min Act: -0.1700
Data Index: 7719653 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.4740. Min Act: -0.1700
Data Index: 1886744 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.3803. Min Act: -0.1700
Data Index: 846288 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.2553. Min Act: -0.1700
Data Index: 2475735 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.1928. Min Act: -0.1700
Data Index: 2052365 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.1928. Min Act: -0.1700
Data Index: 6586397 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.1928. Min Act: -0.1700
Data Index: 6729401 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.1928. Min Act: -0.1700
Data Index: 8324362 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.1928. Min Act: -0.1700
Data Index: 400152 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.1615. Min Act: -0.1700
Data Index: 3284410 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.1615. Min Act: -0.1700
Data Index: 3032404 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0990. Min Act: -0.1700
Data Index: 1195644 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.1303. Min Act: -0.1700
Data Index: 6136293 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0990. Min Act: -0.1700
Data Index: 145931 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0990. Min Act: -0.1700
Data Index: 2531638 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0678. Min Act: -0.1700
Data Index: 8298006 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0990. Min Act: -0.1700
Data Index: 2086224 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0990. Min Act: -0.1700
Data Index: 6429040 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3455698 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4740. Min Range: -5.4740
Max Act: 5.0990. Min Act: -0.1700
Data Index: 2704821 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19