Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.3355. Min Act: -0.1700
Data Index: 4749182 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.2730. Min Act: -0.1700
Data Index: 2935561 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.1792. Min Act: -0.1700
Data Index: 7482396 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.1792. Min Act: -0.1700
Data Index: 4184649 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.1792. Min Act: -0.1700
Data Index: 7968597 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.1167. Min Act: -0.1700
Data Index: 2995658 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.1167. Min Act: -0.1700
Data Index: 4301733 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.1167. Min Act: -0.1700
Data Index: 632357 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.1167. Min Act: -0.1700
Data Index: 2533036 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0855. Min Act: -0.1700
Data Index: 7188157 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0542. Min Act: -0.1700
Data Index: 5163967 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0230. Min Act: -0.1700
Data Index: 5013706 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0230. Min Act: -0.1700
Data Index: 294822 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0230. Min Act: -0.1700
Data Index: 2468689 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0230. Min Act: -0.1700
Data Index: 1888634 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0230. Min Act: -0.1700
Data Index: 3598194 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0230. Min Act: -0.1700
Data Index: 396360 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3355. Min Range: -5.3355
Max Act: 5.0230. Min Act: -0.1700
Data Index: 649360 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3355. Min Range: -5.3355
Max Act: 4.9917. Min Act: -0.1700
Data Index: 7160423 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3355. Min Range: -5.3355
Max Act: 4.9917. Min Act: -0.1700
Data Index: 1653020 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19