Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.7478. Min Act: -0.1700
Data Index: 8399722 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.6228. Min Act: -0.1700
Data Index: 626695 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.5603. Min Act: -0.1700
Data Index: 7349459 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.5915. Min Act: -0.1700
Data Index: 3626909 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.5603. Min Act: -0.1700
Data Index: 6610732 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4978. Min Act: -0.1700
Data Index: 1955117 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4978. Min Act: -0.1700
Data Index: 7564407 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4665. Min Act: -0.1700
Data Index: 4094100 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4665. Min Act: -0.1700
Data Index: 428991 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4665. Min Act: -0.1700
Data Index: 4134217 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4353. Min Act: -0.1700
Data Index: 3108167 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4353. Min Act: -0.1700
Data Index: 6495389 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4040. Min Act: -0.1700
Data Index: 2848373 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4040. Min Act: -0.1700
Data Index: 5856725 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4353. Min Act: -0.1700
Data Index: 8198125 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.3728. Min Act: -0.1700
Data Index: 8138184 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4040. Min Act: -0.1700
Data Index: 5899843 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.4040. Min Act: -0.1700
Data Index: 5419944 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.3728. Min Act: -0.1700
Data Index: 6085209 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7478. Min Range: -4.7478
Max Act: 4.3415. Min Act: -0.1700
Data Index: 1894276 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19