Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2669 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0082. Min Range: -6.0082
Max Act: 6.0082. Min Act: -0.1700
Data Index: 2846283 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.9770. Min Act: -0.1700
Data Index: 2855031 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.8832. Min Act: -0.1700
Data Index: 4125167 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.9145. Min Act: -0.1700
Data Index: 1352749 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.9457. Min Act: -0.1700
Data Index: 3490318 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.9145. Min Act: -0.1700
Data Index: 2275911 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 3280855 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 5989617 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.7895. Min Act: -0.1700
Data Index: 2869927 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 4631897 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.7895. Min Act: -0.1700
Data Index: 2003900 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 1939890 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 1011246 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 7072328 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 8720714 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.6957. Min Act: -0.1700
Data Index: 2311559 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.6957. Min Act: -0.1700
Data Index: 367889 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.7270. Min Act: -0.1700
Data Index: 2999568 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.6957. Min Act: -0.1700
Data Index: 1003511 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0082. Min Range: -6.0082
Max Act: 5.6957. Min Act: -0.1700
Data Index: 5495596 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19