Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2858 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.4898. Min Act: -0.1700
Data Index: 302517 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3335. Min Act: -0.1700
Data Index: 3914328 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3335. Min Act: -0.1700
Data Index: 7633713 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3023. Min Act: -0.1700
Data Index: 599756 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.3023. Min Act: -0.1700
Data Index: 4756552 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.2398. Min Act: -0.1700
Data Index: 1740100 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.2398. Min Act: -0.1700
Data Index: 4429561 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.2085. Min Act: -0.1700
Data Index: 5405601 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.1773. Min Act: -0.1700
Data Index: 4487349 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.1460. Min Act: -0.1700
Data Index: 8512391 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.0835. Min Act: -0.1700
Data Index: 6760681 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.0210. Min Act: -0.1700
Data Index: 580960 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.0523. Min Act: -0.1700
Data Index: 8774819 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.0210. Min Act: -0.1700
Data Index: 5890964 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.0210. Min Act: -0.1700
Data Index: 4614936 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.0210. Min Act: -0.1700
Data Index: 7964293 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.0210. Min Act: -0.1700
Data Index: 7697717 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4898. Min Range: -5.4898
Max Act: 5.0210. Min Act: -0.1700
Data Index: 177982 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4898. Min Range: -5.4898
Max Act: 4.9898. Min Act: -0.1700
Data Index: 1387174 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4898. Min Range: -5.4898
Max Act: 4.9585. Min Act: -0.1700
Data Index: 1108905 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19