Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2038 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.4299. Min Act: -0.1478
Data Index: 5122157 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.4035. Min Act: -0.1700
Data Index: 210652 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3682. Min Act: -0.1698
Data Index: 665173 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3418. Min Act: -0.1693
Data Index: 8695696 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3329. Min Act: -0.1700
Data Index: 1776807 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3329. Min Act: -0.1693
Data Index: 7274183 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3329. Min Act: -0.1644
Data Index: 5472241 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3329. Min Act: -0.1683
Data Index: 5856692 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3241. Min Act: -0.1697
Data Index: 408363 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3241. Min Act: -0.1680
Data Index: 7835619 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3329. Min Act: -0.1511
Data Index: 4806595 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3241. Min Act: -0.1663
Data Index: 7772524 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3241. Min Act: -0.1695
Data Index: 5432304 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3241. Min Act: -0.1511
Data Index: 5122158 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3241. Min Act: -0.1697
Data Index: 4190637 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3153. Min Act: -0.1700
Data Index: 5833008 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3153. Min Act: -0.1623
Data Index: 4004130 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3065. Min Act: -0.1695
Data Index: 6867570 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3065. Min Act: -0.1700
Data Index: 1019724 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4299. Min Range: -1.4299
Max Act: 1.3065. Min Act: -0.1496
Data Index: 5277223 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19