Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1852. Min Range: -7.1852
Max Act: 7.1852. Min Act: -0.1700
Data Index: 930615 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1852. Min Range: -7.1852
Max Act: 7.0914. Min Act: -0.1700
Data Index: 5955048 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.9977. Min Act: -0.1700
Data Index: 779236 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.9664. Min Act: -0.1700
Data Index: 12136 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.9664. Min Act: -0.1700
Data Index: 5510580 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.9039. Min Act: -0.1700
Data Index: 3636012 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.9039. Min Act: -0.1700
Data Index: 621729 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.9352. Min Act: -0.1700
Data Index: 4442563 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.8102. Min Act: -0.1700
Data Index: 4848946 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7789. Min Act: -0.1700
Data Index: 999157 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7164. Min Act: -0.1700
Data Index: 8742878 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7789. Min Act: -0.1700
Data Index: 7820748 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7789. Min Act: -0.1700
Data Index: 2426486 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7789. Min Act: -0.1700
Data Index: 2365856 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7789. Min Act: -0.1700
Data Index: 4760663 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7789. Min Act: -0.1700
Data Index: 3436539 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7477. Min Act: -0.1700
Data Index: 8324196 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7477. Min Act: -0.1700
Data Index: 3135130 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7164. Min Act: -0.1700
Data Index: 394711 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1852. Min Range: -7.1852
Max Act: 6.7164. Min Act: -0.1700
Data Index: 584271 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19