Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.9306. Min Act: -0.1700
Data Index: 6439479 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.9148. Min Act: -0.1700
Data Index: 1999709 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.9306. Min Act: -0.1700
Data Index: 186430 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.9148. Min Act: -0.1700
Data Index: 3758330 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8672. Min Act: -0.1700
Data Index: 610732 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8672. Min Act: -0.1700
Data Index: 7811319 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8195. Min Act: -0.1700
Data Index: 3700592 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8036. Min Act: -0.1700
Data Index: 1879147 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7877. Min Act: -0.1700
Data Index: 7328405 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.8036. Min Act: -0.1700
Data Index: 7241584 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7877. Min Act: -0.1700
Data Index: 869890 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7717. Min Act: -0.1700
Data Index: 3279166 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7717. Min Act: -0.1700
Data Index: 1999702 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7398. Min Act: -0.1700
Data Index: 5243563 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7238. Min Act: -0.1700
Data Index: 1312644 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7078. Min Act: -0.1700
Data Index: 8561451 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7078. Min Act: -0.1700
Data Index: 8010825 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.7078. Min Act: -0.1700
Data Index: 2818760 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.6918. Min Act: -0.1700
Data Index: 6777629 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9306. Min Range: -2.9306
Max Act: 2.6918. Min Act: -0.1700
Data Index: 3157338 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19