Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1769 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3334. Min Range: -6.3334
Max Act: 6.3022. Min Act: -0.1700
Data Index: 4788939 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3334. Min Range: -6.3334
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1392126 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3334. Min Range: -6.3334
Max Act: 6.2084. Min Act: -0.1700
Data Index: 733129 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3334. Min Range: -6.3334
Max Act: 6.1772. Min Act: -0.1700
Data Index: 2661069 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3334. Min Range: -6.3334
Max Act: 6.1147. Min Act: -0.1700
Data Index: 5542981 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3334. Min Range: -6.3334
Max Act: 6.0209. Min Act: -0.1700
Data Index: 406209 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.9584. Min Act: -0.1700
Data Index: 3690115 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8959. Min Act: -0.1700
Data Index: 1970148 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.9272. Min Act: -0.1700
Data Index: 8354158 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8959. Min Act: -0.1700
Data Index: 4491348 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8647. Min Act: -0.1700
Data Index: 2761524 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8647. Min Act: -0.1700
Data Index: 6106474 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8647. Min Act: -0.1700
Data Index: 8722371 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8334. Min Act: -0.1700
Data Index: 5054234 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8334. Min Act: -0.1700
Data Index: 5518813 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8334. Min Act: -0.1700
Data Index: 2060034 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8022. Min Act: -0.1700
Data Index: 7384899 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8022. Min Act: -0.1700
Data Index: 6325861 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8022. Min Act: -0.1700
Data Index: 5377144 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3334. Min Range: -6.3334
Max Act: 5.8022. Min Act: -0.1700
Data Index: 8823005 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19