Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.8980. Min Act: -0.1700
Data Index: 1325185 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.8980. Min Act: -0.1700
Data Index: 1484744 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.7418. Min Act: -0.1700
Data Index: 1306814 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.7730. Min Act: -0.1700
Data Index: 5735381 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.6480. Min Act: -0.1700
Data Index: 4564809 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.7105. Min Act: -0.1700
Data Index: 7400142 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.6168. Min Act: -0.1700
Data Index: 695108 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.5543. Min Act: -0.1700
Data Index: 4350210 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.5543. Min Act: -0.1700
Data Index: 8780859 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.5543. Min Act: -0.1700
Data Index: 4128142 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.5855. Min Act: -0.1700
Data Index: 205585 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.5543. Min Act: -0.1700
Data Index: 2751697 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.5230. Min Act: -0.1700
Data Index: 1385689 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.5230. Min Act: -0.1700
Data Index: 7854270 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.5855. Min Act: -0.1700
Data Index: 8079229 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.4918. Min Act: -0.1700
Data Index: 3112565 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.4293. Min Act: -0.1700
Data Index: 5370815 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.4293. Min Act: -0.1700
Data Index: 2152060 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.3980. Min Act: -0.1700
Data Index: 336142 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8980. Min Range: -5.8980
Max Act: 5.4293. Min Act: -0.1700
Data Index: 3491956 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19