Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3777 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.7289. Min Act: -0.1700
Data Index: 8059498 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.6664. Min Act: -0.1700
Data Index: 2676332 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.6039. Min Act: -0.1700
Data Index: 1750851 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.5414. Min Act: -0.1700
Data Index: 4806201 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.4789. Min Act: -0.1700
Data Index: 7298477 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.4789. Min Act: -0.1700
Data Index: 5289502 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.3539. Min Act: -0.1700
Data Index: 783812 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.3539. Min Act: -0.1700
Data Index: 1000499 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.2914. Min Act: -0.1700
Data Index: 3957857 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.3539. Min Act: -0.1700
Data Index: 2676333 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.2914. Min Act: -0.1696
Data Index: 7082816 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.2289. Min Act: -0.1700
Data Index: 3152003 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.2289. Min Act: -0.1700
Data Index: 7421667 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.2289. Min Act: -0.1700
Data Index: 4806196 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.1039. Min Act: -0.1700
Data Index: 7102325 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.0414. Min Act: -0.1700
Data Index: 3900042 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.0414. Min Act: -0.1700
Data Index: 7296686 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7289. Min Range: -10.7289
Max Act: 10.0414. Min Act: -0.1700
Data Index: 7719497 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7289. Min Range: -10.7289
Max Act: 9.9789. Min Act: -0.1700
Data Index: 1537465 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7289. Min Range: -10.7289
Max Act: 9.9789. Min Act: -0.1700
Data Index: 3218324 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19