Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.6291. Min Act: -0.1700
Data Index: 4237631 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.4416. Min Act: -0.1700
Data Index: 8779798 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.3791. Min Act: -0.1700
Data Index: 7595951 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.3478. Min Act: -0.1700
Data Index: 4594170 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.3791. Min Act: -0.1700
Data Index: 7780949 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.3478. Min Act: -0.1700
Data Index: 2892623 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.2541. Min Act: -0.1700
Data Index: 7714503 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.2228. Min Act: -0.1700
Data Index: 359326 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.2228. Min Act: -0.1700
Data Index: 1847029 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.1603. Min Act: -0.1700
Data Index: 7197604 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.1916. Min Act: -0.1700
Data Index: 1528511 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.1603. Min Act: -0.1700
Data Index: 3752246 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.1916. Min Act: -0.1700
Data Index: 4006279 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.1291. Min Act: -0.1700
Data Index: 915300 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.1291. Min Act: -0.1700
Data Index: 1977475 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.1603. Min Act: -0.1700
Data Index: 5005797 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.1603. Min Act: -0.1700
Data Index: 6068004 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.0978. Min Act: -0.1700
Data Index: 2322993 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.0978. Min Act: -0.1700
Data Index: 5219267 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6291. Min Range: -5.6291
Max Act: 5.0978. Min Act: -0.1700
Data Index: 5011953 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19