Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.7639. Min Act: -0.1700
Data Index: 4584371 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.7014. Min Act: -0.1700
Data Index: 3237081 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.5451. Min Act: -0.1700
Data Index: 2508606 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.4826. Min Act: -0.1700
Data Index: 583141 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.4826. Min Act: -0.1700
Data Index: 4455636 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.4826. Min Act: -0.1700
Data Index: 5691186 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.4514. Min Act: -0.1700
Data Index: 1190755 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.4201. Min Act: -0.1700
Data Index: 4906897 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.4514. Min Act: -0.1700
Data Index: 1049031 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.4201. Min Act: -0.1700
Data Index: 2655518 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.4514. Min Act: -0.1700
Data Index: 3105685 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.3889. Min Act: -0.1700
Data Index: 3366049 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.3576. Min Act: -0.1700
Data Index: 5704091 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2951. Min Act: -0.1700
Data Index: 755319 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2951. Min Act: -0.1700
Data Index: 4201224 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2951. Min Act: -0.1700
Data Index: 4189317 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2639. Min Act: -0.1700
Data Index: 8203717 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2639. Min Act: -0.1700
Data Index: 8284968 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2639. Min Act: -0.1700
Data Index: 5870855 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7639. Min Range: -6.7639
Max Act: 6.2326. Min Act: -0.1700
Data Index: 2382882 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19