Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1610 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.4302. Min Act: -0.1700
Data Index: 8703003 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.3990. Min Act: -0.1700
Data Index: 6179579 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.3677. Min Act: -0.1700
Data Index: 256711 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.3677. Min Act: -0.1700
Data Index: 7266235 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.3365. Min Act: -0.1700
Data Index: 1609600 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.3052. Min Act: -0.1700
Data Index: 6679380 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.2427. Min Act: -0.1700
Data Index: 5838311 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.2115. Min Act: -0.1700
Data Index: 5822729 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1802. Min Act: -0.1700
Data Index: 6942664 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.2115. Min Act: -0.1700
Data Index: 8261302 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1802. Min Act: -0.1700
Data Index: 7822333 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1802. Min Act: -0.1700
Data Index: 1565655 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1490. Min Act: -0.1700
Data Index: 7937162 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1490. Min Act: -0.1700
Data Index: 3048571 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1490. Min Act: -0.1700
Data Index: 1568437 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1490. Min Act: -0.1700
Data Index: 89689 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1177. Min Act: -0.1700
Data Index: 4675899 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.1177. Min Act: -0.1700
Data Index: 1190822 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.0865. Min Act: -0.1700
Data Index: 3333545 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4302. Min Range: -5.4302
Max Act: 5.0865. Min Act: -0.1700
Data Index: 5293829 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19