Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.6036. Min Act: -0.1700
Data Index: 2414395 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.6348. Min Act: -0.1700
Data Index: 3639062 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.5723. Min Act: -0.1700
Data Index: 1907516 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4786. Min Act: -0.1700
Data Index: 8280235 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4786. Min Act: -0.1700
Data Index: 1221373 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4786. Min Act: -0.1700
Data Index: 3493804 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4161. Min Act: -0.1700
Data Index: 4394829 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4473. Min Act: -0.1700
Data Index: 1221372 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4161. Min Act: -0.1700
Data Index: 2560198 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4161. Min Act: -0.1700
Data Index: 7666868 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4161. Min Act: -0.1700
Data Index: 7001320 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4161. Min Act: -0.1700
Data Index: 8325147 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3848. Min Act: -0.1700
Data Index: 4858191 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3848. Min Act: -0.1700
Data Index: 1967021 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3536. Min Act: -0.1700
Data Index: 6660198 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3848. Min Act: -0.1700
Data Index: 6755536 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3848. Min Act: -0.1700
Data Index: 2164283 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3536. Min Act: -0.1700
Data Index: 1453204 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3536. Min Act: -0.1700
Data Index: 2085319 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3536. Min Act: -0.1700
Data Index: 3011945 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19