Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2387 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.6848. Min Act: -0.1700
Data Index: 3745632 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.3098. Min Act: -0.1700
Data Index: 2706140 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.2473. Min Act: -0.1700
Data Index: 6795659 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.2473. Min Act: -0.1700
Data Index: 5146106 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.1848. Min Act: -0.1700
Data Index: 7570495 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.1223. Min Act: -0.1700
Data Index: 3882342 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.1223. Min Act: -0.1700
Data Index: 1059368 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.1223. Min Act: -0.1700
Data Index: 1628206 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.0598. Min Act: -0.1700
Data Index: 1286837 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.0598. Min Act: -0.1700
Data Index: 3553730 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6848. Min Range: -10.6848
Max Act: 10.1223. Min Act: -0.1700
Data Index: 4527689 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.9973. Min Act: -0.1700
Data Index: 6598904 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.9973. Min Act: -0.1700
Data Index: 6817309 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.9348. Min Act: -0.1700
Data Index: 1591455 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.9348. Min Act: -0.1700
Data Index: 6374865 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.9348. Min Act: -0.1700
Data Index: 8611813 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.9348. Min Act: -0.1700
Data Index: 5762307 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.8098. Min Act: -0.1700
Data Index: 6491191 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.8723. Min Act: -0.1700
Data Index: 5484630 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6848. Min Range: -10.6848
Max Act: 9.8723. Min Act: -0.1700
Data Index: 2513747 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19