Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1980 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7145. Min Range: -7.7145
Max Act: 7.7145. Min Act: -0.1700
Data Index: 2815999 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7145. Min Range: -7.7145
Max Act: 7.4957. Min Act: -0.1700
Data Index: 6119830 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7145. Min Range: -7.7145
Max Act: 7.3395. Min Act: -0.1700
Data Index: 3477388 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7145. Min Range: -7.7145
Max Act: 7.0895. Min Act: -0.1700
Data Index: 4362125 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7145. Min Range: -7.7145
Max Act: 7.0270. Min Act: -0.1700
Data Index: 4297332 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7145. Min Range: -7.7145
Max Act: 7.0270. Min Act: -0.1700
Data Index: 2687916 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.9957. Min Act: -0.1700
Data Index: 4769031 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.9332. Min Act: -0.1700
Data Index: 5375065 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.9645. Min Act: -0.1700
Data Index: 7910989 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.9332. Min Act: -0.1700
Data Index: 4536757 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.9020. Min Act: -0.1700
Data Index: 4223112 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.8707. Min Act: -0.1700
Data Index: 2747679 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.8082. Min Act: -0.1700
Data Index: 7061977 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.8395. Min Act: -0.1700
Data Index: 7446265 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.8395. Min Act: -0.1700
Data Index: 4378582 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.7770. Min Act: -0.1700
Data Index: 4945994 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.7770. Min Act: -0.1700
Data Index: 8828036 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.7145. Min Act: -0.1700
Data Index: 5461880 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.7145. Min Act: -0.1700
Data Index: 8469157 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7145. Min Range: -7.7145
Max Act: 6.7145. Min Act: -0.1700
Data Index: 4980449 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19