Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.7458. Min Act: -0.1700
Data Index: 584626 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.7458. Min Act: -0.1700
Data Index: 7995653 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.7145. Min Act: -0.1700
Data Index: 2951513 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.7145. Min Act: -0.1700
Data Index: 7552118 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.7145. Min Act: -0.1700
Data Index: 2381667 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.7145. Min Act: -0.1700
Data Index: 13861 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.6833. Min Act: -0.1700
Data Index: 6215933 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.6833. Min Act: -0.1700
Data Index: 8446443 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.6520. Min Act: -0.1700
Data Index: 6389581 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.6520. Min Act: -0.1700
Data Index: 5690840 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.6520. Min Act: -0.1700
Data Index: 172426 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.6208. Min Act: -0.1700
Data Index: 2746940 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.6208. Min Act: -0.1700
Data Index: 2201874 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.5583. Min Act: -0.1700
Data Index: 3254817 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.5583. Min Act: -0.1700
Data Index: 7281259 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.5583. Min Act: -0.1700
Data Index: 1755068 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.5270. Min Act: -0.1700
Data Index: 1015116 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.5270. Min Act: -0.1700
Data Index: 4580656 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.5270. Min Act: -0.1700
Data Index: 2876287 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7458. Min Range: -6.7458
Max Act: 6.4645. Min Act: -0.1700
Data Index: 4448460 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19