Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0019. Min Range: -7.0019
Max Act: 7.0019. Min Act: -0.1700
Data Index: 720690 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0019. Min Range: -7.0019
Max Act: 7.0019. Min Act: -0.1700
Data Index: 6659509 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.8769. Min Act: -0.1700
Data Index: 8038637 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.8144. Min Act: -0.1700
Data Index: 6037324 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.8144. Min Act: -0.1700
Data Index: 2641583 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.7206. Min Act: -0.1700
Data Index: 5734702 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.7206. Min Act: -0.1700
Data Index: 248280 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.6581. Min Act: -0.1700
Data Index: 6929191 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.6269. Min Act: -0.1700
Data Index: 2012975 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.6269. Min Act: -0.1700
Data Index: 1188231 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5644. Min Act: -0.1700
Data Index: 8489453 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5644. Min Act: -0.1700
Data Index: 6685789 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5331. Min Act: -0.1700
Data Index: 1537994 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5956. Min Act: -0.1700
Data Index: 7858191 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5644. Min Act: -0.1700
Data Index: 7912832 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5331. Min Act: -0.1700
Data Index: 3615365 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5331. Min Act: -0.1700
Data Index: 3805260 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5644. Min Act: -0.1700
Data Index: 7548431 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5331. Min Act: -0.1700
Data Index: 2498522 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0019. Min Range: -7.0019
Max Act: 6.5331. Min Act: -0.1700
Data Index: 4979464 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19