Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2207. Min Range: -9.2207
Max Act: 9.2207. Min Act: -0.1700
Data Index: 1106515 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.7832. Min Act: -0.1700
Data Index: 5702366 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.7207. Min Act: -0.1700
Data Index: 3023298 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.6582. Min Act: -0.1700
Data Index: 7831057 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.5957. Min Act: -0.1700
Data Index: 3192141 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.5332. Min Act: -0.1700
Data Index: 2914091 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.5332. Min Act: -0.1700
Data Index: 1386103 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.4082. Min Act: -0.1700
Data Index: 1855930 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.4707. Min Act: -0.1700
Data Index: 773957 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.4082. Min Act: -0.1700
Data Index: 4621485 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.3457. Min Act: -0.1700
Data Index: 1145830 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.3457. Min Act: -0.1700
Data Index: 8094838 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.3457. Min Act: -0.1700
Data Index: 5012257 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.2832. Min Act: -0.1700
Data Index: 2178731 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.2207. Min Act: -0.1700
Data Index: 2414050 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.2207. Min Act: -0.1700
Data Index: 5775123 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.1582. Min Act: -0.1700
Data Index: 3800521 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.1582. Min Act: -0.1700
Data Index: 7003086 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.0957. Min Act: -0.1700
Data Index: 7140384 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2207. Min Range: -9.2207
Max Act: 8.0957. Min Act: -0.1700
Data Index: 7823545 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19