Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1278 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3005. Min Range: -6.3005
Max Act: 6.3005. Min Act: -0.1700
Data Index: 3591335 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3005. Min Range: -6.3005
Max Act: 6.1442. Min Act: -0.1700
Data Index: 8641893 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9567. Min Act: -0.1700
Data Index: 230336 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9567. Min Act: -0.1700
Data Index: 1051194 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.9255. Min Act: -0.1700
Data Index: 1299638 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8942. Min Act: -0.1700
Data Index: 3001379 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8942. Min Act: -0.1700
Data Index: 2037013 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8942. Min Act: -0.1700
Data Index: 7292372 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8630. Min Act: -0.1700
Data Index: 8476998 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8317. Min Act: -0.1700
Data Index: 7195140 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8317. Min Act: -0.1700
Data Index: 1781207 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.8005. Min Act: -0.1700
Data Index: 6354914 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.7692. Min Act: -0.1700
Data Index: 1650331 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.7692. Min Act: -0.1700
Data Index: 2746578 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.7067. Min Act: -0.1700
Data Index: 5013817 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.7380. Min Act: -0.1700
Data Index: 1832749 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.7380. Min Act: -0.1700
Data Index: 7083872 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.7067. Min Act: -0.1700
Data Index: 6498377 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.7067. Min Act: -0.1700
Data Index: 7023568 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3005. Min Range: -6.3005
Max Act: 5.7067. Min Act: -0.1700
Data Index: 2012988 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19