Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.9670. Min Act: -0.1700
Data Index: 5509490 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.9357. Min Act: -0.1700
Data Index: 6191038 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.8107. Min Act: -0.1700
Data Index: 4776498 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.9045. Min Act: -0.1700
Data Index: 255720 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.8107. Min Act: -0.1700
Data Index: 746047 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.8107. Min Act: -0.1700
Data Index: 4776515 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.7482. Min Act: -0.1700
Data Index: 6853721 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.7482. Min Act: -0.1700
Data Index: 214205 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.7482. Min Act: -0.1700
Data Index: 1028856 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.7482. Min Act: -0.1700
Data Index: 746048 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.6545. Min Act: -0.1700
Data Index: 469643 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.6232. Min Act: -0.1700
Data Index: 4462718 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.6232. Min Act: -0.1700
Data Index: 4776502 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.5920. Min Act: -0.1700
Data Index: 8544785 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.6232. Min Act: -0.1700
Data Index: 499697 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.5295. Min Act: -0.1700
Data Index: 3117325 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.5607. Min Act: -0.1700
Data Index: 4776499 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.5295. Min Act: -0.1700
Data Index: 4462686 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.4982. Min Act: -0.1700
Data Index: 2196865 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9670. Min Range: -5.9670
Max Act: 5.4982. Min Act: -0.1700
Data Index: 3117323 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19