Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4461. Min Act: -0.1700
Data Index: 4725867 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4285. Min Act: -0.1694
Data Index: 5096882 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4197. Min Act: -0.1700
Data Index: 6198530 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4109. Min Act: -0.1697
Data Index: 2151527 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4197. Min Act: -0.1695
Data Index: 3216716 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4021. Min Act: -0.1693
Data Index: 2881462 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4109. Min Act: -0.1698
Data Index: 5729980 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4109. Min Act: -0.1693
Data Index: 4228330 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.4021. Min Act: -0.1700
Data Index: 1493042 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3933. Min Act: -0.1700
Data Index: 1064338 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3933. Min Act: -0.1690
Data Index: 2041817 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3845. Min Act: -0.1683
Data Index: 893319 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3757. Min Act: -0.1697
Data Index: 8760611 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3845. Min Act: -0.1698
Data Index: 893344 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3757. Min Act: -0.1686
Data Index: 2607496 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3933. Min Act: -0.1697
Data Index: 7400263 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3845. Min Act: -0.1700
Data Index: 7273734 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3845. Min Act: -0.1700
Data Index: 6800371 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3845. Min Act: -0.1698
Data Index: 6668564 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4461. Min Range: -1.4461
Max Act: 1.3757. Min Act: -0.1700
Data Index: 3419273 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19