Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.7535. Min Act: -0.1700
Data Index: 2623342 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.7223. Min Act: -0.1700
Data Index: 7008051 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.6910. Min Act: -0.1700
Data Index: 8806796 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.6598. Min Act: -0.1700
Data Index: 8381475 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.5973. Min Act: -0.1700
Data Index: 6465256 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.5973. Min Act: -0.1700
Data Index: 3165668 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.5973. Min Act: -0.1700
Data Index: 4655965 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.5660. Min Act: -0.1700
Data Index: 7484455 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.5348. Min Act: -0.1700
Data Index: 2911030 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.3785. Min Act: -0.1700
Data Index: 3746453 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.3473. Min Act: -0.1700
Data Index: 5513147 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.3160. Min Act: -0.1700
Data Index: 2914908 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.2848. Min Act: -0.1700
Data Index: 3799294 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.2848. Min Act: -0.1700
Data Index: 6734878 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.1910. Min Act: -0.1700
Data Index: 787315 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.1910. Min Act: -0.1700
Data Index: 6247671 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.1598. Min Act: -0.1700
Data Index: 5370077 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.1598. Min Act: -0.1700
Data Index: 5934233 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.1285. Min Act: -0.1700
Data Index: 6875820 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7535. Min Range: -6.7535
Max Act: 6.0973. Min Act: -0.1700
Data Index: 1426894 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19