Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.5397. Min Act: -0.1700
Data Index: 403630 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.5084. Min Act: -0.1700
Data Index: 403627 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.4147. Min Act: -0.1700
Data Index: 6142146 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.3834. Min Act: -0.1700
Data Index: 4916821 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.3834. Min Act: -0.1700
Data Index: 4916820 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.3522. Min Act: -0.1700
Data Index: 403628 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2584. Min Act: -0.1700
Data Index: 4916819 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2584. Min Act: -0.1700
Data Index: 6142145 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2584. Min Act: -0.1700
Data Index: 3417023 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2584. Min Act: -0.1700
Data Index: 7760319 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2584. Min Act: -0.1700
Data Index: 1648820 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2272. Min Act: -0.1700
Data Index: 3620023 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2272. Min Act: -0.1700
Data Index: 6142144 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2272. Min Act: -0.1700
Data Index: 3323 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2272. Min Act: -0.1700
Data Index: 5516815 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2272. Min Act: -0.1700
Data Index: 1141296 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2272. Min Act: -0.1700
Data Index: 6234556 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2272. Min Act: -0.1700
Data Index: 2496903 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.2272. Min Act: -0.1700
Data Index: 6234559 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5397. Min Range: -5.5397
Max Act: 5.1959. Min Act: -0.1699
Data Index: 4240914 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19