Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2289. Min Range: -8.2289
Max Act: 8.2289. Min Act: -0.1700
Data Index: 3805268 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2289. Min Range: -8.2289
Max Act: 8.1976. Min Act: -0.1700
Data Index: 8261777 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2289. Min Range: -8.2289
Max Act: 8.0726. Min Act: -0.1700
Data Index: 6237311 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2289. Min Range: -8.2289
Max Act: 8.0101. Min Act: -0.1700
Data Index: 5108914 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.9476. Min Act: -0.1700
Data Index: 6243079 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.9789. Min Act: -0.1696
Data Index: 732628 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.9476. Min Act: -0.1695
Data Index: 7102822 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7914. Min Act: -0.1699
Data Index: 5953516 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7914. Min Act: -0.1699
Data Index: 241312 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7914. Min Act: -0.1700
Data Index: 3805267 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7601. Min Act: -0.1700
Data Index: 3407048 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7601. Min Act: -0.1700
Data Index: 883867 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7601. Min Act: -0.1700
Data Index: 8448344 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7601. Min Act: -0.1693
Data Index: 3266292 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7289. Min Act: -0.1700
Data Index: 3485482 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.7289. Min Act: -0.1699
Data Index: 5509564 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.6976. Min Act: -0.1700
Data Index: 3873584 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.6976. Min Act: -0.1700
Data Index: 8548681 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.6664. Min Act: -0.1699
Data Index: 7109092 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2289. Min Range: -8.2289
Max Act: 7.6351. Min Act: -0.1699
Data Index: 1066563 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19