Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4271 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.6732. Min Act: -0.1700
Data Index: 7029594 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.6107. Min Act: -0.1700
Data Index: 57997 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.6107. Min Act: -0.1700
Data Index: 539587 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5170. Min Act: -0.1700
Data Index: 1970295 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5170. Min Act: -0.1700
Data Index: 6134483 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4857. Min Act: -0.1700
Data Index: 1274190 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4857. Min Act: -0.1700
Data Index: 5806651 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4545. Min Act: -0.1700
Data Index: 1909453 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4232. Min Act: -0.1700
Data Index: 2548179 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4545. Min Act: -0.1700
Data Index: 2626475 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4545. Min Act: -0.1700
Data Index: 1555275 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4545. Min Act: -0.1700
Data Index: 5257381 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.3920. Min Act: -0.1700
Data Index: 6832097 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4232. Min Act: -0.1700
Data Index: 1625670 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4545. Min Act: -0.1700
Data Index: 57998 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4545. Min Act: -0.1700
Data Index: 3728141 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.3920. Min Act: -0.1700
Data Index: 8394605 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.3607. Min Act: -0.1700
Data Index: 5125894 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.3294. Min Act: -0.1700
Data Index: 4201156 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.3607. Min Act: -0.1700
Data Index: 1347088 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19