Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2457 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.8971. Min Act: -0.1700
Data Index: 1332431 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.8658. Min Act: -0.1700
Data Index: 6620305 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.8658. Min Act: -0.1700
Data Index: 5608550 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.8658. Min Act: -0.1700
Data Index: 2107820 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.8345. Min Act: -0.1700
Data Index: 8044412 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.8032. Min Act: -0.1700
Data Index: 2408896 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.8345. Min Act: -0.1700
Data Index: 2340365 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.8032. Min Act: -0.1700
Data Index: 7043157 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.7720. Min Act: -0.1700
Data Index: 8063632 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.7720. Min Act: -0.1700
Data Index: 5998444 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.7720. Min Act: -0.1700
Data Index: 6893093 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.7094. Min Act: -0.1700
Data Index: 7231971 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.7407. Min Act: -0.1700
Data Index: 7372837 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.6938. Min Act: -0.1700
Data Index: 2062968 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.7250. Min Act: -0.1700
Data Index: 3414878 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.7094. Min Act: -0.1700
Data Index: 4265905 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.7250. Min Act: -0.1700
Data Index: 954795 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.6781. Min Act: -0.1700
Data Index: 663030 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.6781. Min Act: -0.1700
Data Index: 4514197 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8971. Min Range: -3.8971
Max Act: 3.6625. Min Act: -0.1700
Data Index: 5776770 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19