Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.9289. Min Act: -0.1700
Data Index: 7352237 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.6789. Min Act: -0.1700
Data Index: 3046319 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.6164. Min Act: -0.1700
Data Index: 2892888 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.5852. Min Act: -0.1700
Data Index: 3680088 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.5539. Min Act: -0.1700
Data Index: 8480151 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4914. Min Act: -0.1700
Data Index: 3516879 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4602. Min Act: -0.1700
Data Index: 2987759 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.5227. Min Act: -0.1700
Data Index: 1482720 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4602. Min Act: -0.1700
Data Index: 8506252 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4289. Min Act: -0.1700
Data Index: 6015307 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4602. Min Act: -0.1700
Data Index: 1197468 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4289. Min Act: -0.1700
Data Index: 1226203 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4289. Min Act: -0.1700
Data Index: 3959420 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4289. Min Act: -0.1700
Data Index: 5269037 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.4289. Min Act: -0.1700
Data Index: 8264954 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.3977. Min Act: -0.1700
Data Index: 4952189 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.3977. Min Act: -0.1700
Data Index: 3354292 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.3977. Min Act: -0.1700
Data Index: 3592505 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.3977. Min Act: -0.1700
Data Index: 8046930 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9289. Min Range: -4.9289
Max Act: 4.3977. Min Act: -0.1700
Data Index: 801691 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19