Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 535 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1391. Min Range: -8.1391
Max Act: 8.1391. Min Act: -0.0831
Data Index: 8064007 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1391. Min Range: -8.1391
Max Act: 8.0453. Min Act: -0.1676
Data Index: 6442748 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.9828. Min Act: -0.1691
Data Index: 4844576 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1391. Min Range: -8.1391
Max Act: 8.0453. Min Act: -0.1700
Data Index: 5875622 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1391. Min Range: -8.1391
Max Act: 8.0141. Min Act: -0.1574
Data Index: 1893727 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.9828. Min Act: -0.1020
Data Index: 3092618 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1391. Min Range: -8.1391
Max Act: 8.0141. Min Act: -0.1694
Data Index: 6357106 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.9516. Min Act: -0.1698
Data Index: 6357107 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.9516. Min Act: -0.1629
Data Index: 6412866 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.9516. Min Act: -0.1636
Data Index: 3007394 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.9516. Min Act: -0.1700
Data Index: 8227135 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.9203. Min Act: -0.1700
Data Index: 7801025 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.8891. Min Act: -0.1430
Data Index: 7565564 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.8891. Min Act: -0.1592
Data Index: 4867277 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.8578. Min Act: -0.1686
Data Index: 2999311 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.8578. Min Act: -0.1088
Data Index: 1567730 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.8891. Min Act: -0.0321
Data Index: 1031846 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.8891. Min Act: -0.1700
Data Index: 3919080 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.8891. Min Act: -0.1698
Data Index: 3024227 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1391. Min Range: -8.1391
Max Act: 7.8891. Min Act: -0.0996
Data Index: 6497064 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19