Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 592 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.7335. Min Act: -0.1700
Data Index: 6940890 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.6085. Min Act: -0.1700
Data Index: 4352527 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.5460. Min Act: -0.1700
Data Index: 3609034 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.5460. Min Act: -0.1700
Data Index: 7766346 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.5460. Min Act: -0.1700
Data Index: 1913909 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.5460. Min Act: -0.1700
Data Index: 4903961 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.5460. Min Act: -0.1700
Data Index: 2407746 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4835. Min Act: -0.1700
Data Index: 7431814 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4210. Min Act: -0.1700
Data Index: 6855000 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4835. Min Act: -0.1700
Data Index: 5432707 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4210. Min Act: -0.1700
Data Index: 6818679 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4210. Min Act: -0.1700
Data Index: 3519193 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.3585. Min Act: -0.1700
Data Index: 6595319 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4210. Min Act: -0.1700
Data Index: 8554548 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4210. Min Act: -0.1700
Data Index: 6038147 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4210. Min Act: -0.1700
Data Index: 8832470 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.4210. Min Act: -0.1700
Data Index: 4603748 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.3585. Min Act: -0.1700
Data Index: 383304 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.3585. Min Act: -0.1700
Data Index: 2824242 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7335. Min Range: -8.7335
Max Act: 8.3585. Min Act: -0.1700
Data Index: 6589151 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19