Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4982. Min Act: -0.1700
Data Index: 667261 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4982. Min Act: -0.1700
Data Index: 4233349 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4982. Min Act: -0.1700
Data Index: 1237215 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4982. Min Act: -0.1700
Data Index: 5640285 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4658. Min Act: -0.1700
Data Index: 4023795 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4820. Min Act: -0.1700
Data Index: 3047538 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4658. Min Act: -0.1700
Data Index: 7713700 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4820. Min Act: -0.1700
Data Index: 7916434 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4820. Min Act: -0.1700
Data Index: 5567743 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4658. Min Act: -0.1700
Data Index: 22754 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4658. Min Act: -0.1700
Data Index: 22771 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4658. Min Act: -0.1700
Data Index: 4023805 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4495. Min Act: -0.1700
Data Index: 7599441 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4333. Min Act: -0.1700
Data Index: 4023796 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4495. Min Act: -0.1700
Data Index: 4023797 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4495. Min Act: -0.1700
Data Index: 5670454 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4495. Min Act: -0.1700
Data Index: 4023794 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4495. Min Act: -0.1700
Data Index: 4233336 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4495. Min Act: -0.1700
Data Index: 932882 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4982. Min Range: -2.4982
Max Act: 2.4170. Min Act: -0.1700
Data Index: 4233334 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19