Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1004 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.2207. Min Act: -0.1700
Data Index: 4777857 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.2207. Min Act: -0.1700
Data Index: 6695597 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.1269. Min Act: -0.1700
Data Index: 5092654 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.1269. Min Act: -0.1700
Data Index: 8327970 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0957. Min Act: -0.1700
Data Index: 4700363 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0957. Min Act: -0.1700
Data Index: 8704412 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0957. Min Act: -0.1700
Data Index: 5131911 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0957. Min Act: -0.1700
Data Index: 8685892 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0332. Min Act: -0.1700
Data Index: 5183357 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0644. Min Act: -0.1700
Data Index: 6622894 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0332. Min Act: -0.1700
Data Index: 4777859 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0644. Min Act: -0.1700
Data Index: 8624159 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0332. Min Act: -0.1700
Data Index: 8685908 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0332. Min Act: -0.1700
Data Index: 183182 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0644. Min Act: -0.1700
Data Index: 1757160 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0019. Min Act: -0.1700
Data Index: 4785954 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0332. Min Act: -0.1700
Data Index: 2906682 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0332. Min Act: -0.1700
Data Index: 6663072 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0644. Min Act: -0.1700
Data Index: 1673408 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2207. Min Range: -4.2207
Max Act: 4.0644. Min Act: -0.1700
Data Index: 6021786 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19