Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.6345. Min Act: -0.1700
Data Index: 1654919 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.6032. Min Act: -0.1700
Data Index: 5459733 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.5720. Min Act: -0.1700
Data Index: 2275019 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.5095. Min Act: -0.1700
Data Index: 68668 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.5095. Min Act: -0.1700
Data Index: 1561329 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.5095. Min Act: -0.1700
Data Index: 7038746 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.5095. Min Act: -0.1700
Data Index: 8540309 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.4782. Min Act: -0.1700
Data Index: 4467702 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.4470. Min Act: -0.1700
Data Index: 5081476 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.4470. Min Act: -0.1700
Data Index: 7136392 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.4470. Min Act: -0.1700
Data Index: 2065554 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.4470. Min Act: -0.1700
Data Index: 3433004 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.4157. Min Act: -0.1700
Data Index: 389807 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.3532. Min Act: -0.1700
Data Index: 2361685 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.3532. Min Act: -0.1700
Data Index: 7098910 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.3532. Min Act: -0.1700
Data Index: 6288830 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.3220. Min Act: -0.1700
Data Index: 2164897 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.3532. Min Act: -0.1700
Data Index: 6382199 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.3220. Min Act: -0.1700
Data Index: 1692514 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6345. Min Range: -6.6345
Max Act: 6.3532. Min Act: -0.1700
Data Index: 1645310 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19