Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4973 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.8732. Min Act: -0.1700
Data Index: 167942 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.8107. Min Act: -0.1700
Data Index: 4771317 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7170. Min Act: -0.1700
Data Index: 6397331 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.7170. Min Act: -0.1700
Data Index: 7005880 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6857. Min Act: -0.1700
Data Index: 6069639 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6545. Min Act: -0.1700
Data Index: 735379 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6232. Min Act: -0.1700
Data Index: 3481629 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5920. Min Act: -0.1700
Data Index: 6397336 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.6232. Min Act: -0.1700
Data Index: 8142776 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5920. Min Act: -0.1700
Data Index: 4495349 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5607. Min Act: -0.1700
Data Index: 3776968 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5607. Min Act: -0.1700
Data Index: 2634576 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5295. Min Act: -0.1700
Data Index: 3776971 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5607. Min Act: -0.1700
Data Index: 1347116 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5295. Min Act: -0.1700
Data Index: 735370 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5607. Min Act: -0.1700
Data Index: 4546558 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5295. Min Act: -0.1700
Data Index: 6397334 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5295. Min Act: -0.1700
Data Index: 6397335 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.5295. Min Act: -0.1700
Data Index: 6397329 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8732. Min Range: -4.8732
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5182809 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19