Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1078. Min Range: -6.1078
Max Act: 6.1078. Min Act: -0.1700
Data Index: 6731955 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.9828. Min Act: -0.1700
Data Index: 2396269 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.8890. Min Act: -0.1700
Data Index: 3844810 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.7953. Min Act: -0.1700
Data Index: 8553114 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.7640. Min Act: -0.1700
Data Index: 4068370 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.7328. Min Act: -0.1700
Data Index: 3856793 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.7015. Min Act: -0.1699
Data Index: 7190253 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.6390. Min Act: -0.1700
Data Index: 5813710 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.6390. Min Act: -0.1700
Data Index: 7015548 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.6078. Min Act: -0.1700
Data Index: 892583 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.6078. Min Act: -0.1700
Data Index: 3632869 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.6078. Min Act: -0.1700
Data Index: 544839 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.5765. Min Act: -0.1700
Data Index: 4302217 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.6078. Min Act: -0.1700
Data Index: 3318826 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.5453. Min Act: -0.1700
Data Index: 6570160 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.5453. Min Act: -0.1700
Data Index: 4403860 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.5140. Min Act: -0.1700
Data Index: 7999197 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.4828. Min Act: -0.1700
Data Index: 5399749 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.5140. Min Act: -0.1700
Data Index: 1318330 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1078. Min Range: -6.1078
Max Act: 5.4828. Min Act: -0.1700
Data Index: 5829253 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19