Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4708 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.6248. Min Act: -0.1700
Data Index: 1555895 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.4685. Min Act: -0.1700
Data Index: 7805090 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.4373. Min Act: -0.1700
Data Index: 1350554 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.4373. Min Act: -0.1700
Data Index: 3456668 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.4685. Min Act: -0.1700
Data Index: 3619059 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.4060. Min Act: -0.1700
Data Index: 5342556 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3748. Min Act: -0.1700
Data Index: 4701598 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3435. Min Act: -0.1700
Data Index: 8429026 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3435. Min Act: -0.1700
Data Index: 6986079 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3123. Min Act: -0.1700
Data Index: 6959236 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 8682299 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3123. Min Act: -0.1700
Data Index: 2348878 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.3123. Min Act: -0.1700
Data Index: 8827577 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 8256424 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 7343775 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 5080858 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 8169289 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2810. Min Act: -0.1700
Data Index: 1401499 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2185. Min Act: -0.1700
Data Index: 375735 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6248. Min Range: -6.6248
Max Act: 6.2498. Min Act: -0.1700
Data Index: 1800951 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19