Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.5882. Min Act: -0.1700
Data Index: 4490235 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.4319. Min Act: -0.1700
Data Index: 3582443 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.3069. Min Act: -0.1700
Data Index: 1220390 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.2444. Min Act: -0.1700
Data Index: 1729791 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.2444. Min Act: -0.1700
Data Index: 1453778 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.1194. Min Act: -0.1700
Data Index: 1855864 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0882. Min Act: -0.1700
Data Index: 7200366 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0882. Min Act: -0.1700
Data Index: 3724486 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0882. Min Act: -0.1700
Data Index: 8828864 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0569. Min Act: -0.1700
Data Index: 6199601 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0569. Min Act: -0.1700
Data Index: 5683728 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0569. Min Act: -0.1700
Data Index: 7134952 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0569. Min Act: -0.1700
Data Index: 2103493 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0569. Min Act: -0.1700
Data Index: 6965488 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0569. Min Act: -0.1700
Data Index: 8182631 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0257. Min Act: -0.1700
Data Index: 3316119 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0257. Min Act: -0.1700
Data Index: 8224374 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5882. Min Range: -7.5882
Max Act: 7.0257. Min Act: -0.1700
Data Index: 4517360 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5882. Min Range: -7.5882
Max Act: 6.9944. Min Act: -0.1700
Data Index: 1763834 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5882. Min Range: -7.5882
Max Act: 6.9632. Min Act: -0.1700
Data Index: 6716871 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19