Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1507 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.4978. Min Act: -0.1700
Data Index: 7811521 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.4040. Min Act: -0.1700
Data Index: 1000474 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.3728. Min Act: -0.1700
Data Index: 5400540 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.4040. Min Act: -0.1700
Data Index: 7723663 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.3415. Min Act: -0.1700
Data Index: 205094 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.2790. Min Act: -0.1700
Data Index: 7911425 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.2790. Min Act: -0.1700
Data Index: 6300582 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.2165. Min Act: -0.1700
Data Index: 8482852 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.2165. Min Act: -0.1700
Data Index: 2540513 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.2165. Min Act: -0.1700
Data Index: 2104061 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.2165. Min Act: -0.1700
Data Index: 7236589 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.2165. Min Act: -0.1700
Data Index: 8259172 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.1853. Min Act: -0.1700
Data Index: 3827383 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.1540. Min Act: -0.1700
Data Index: 4797983 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.1540. Min Act: -0.1700
Data Index: 4091576 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.1853. Min Act: -0.1700
Data Index: 7646189 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.1540. Min Act: -0.1700
Data Index: 747829 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.1540. Min Act: -0.1700
Data Index: 6897682 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.1228. Min Act: -0.1700
Data Index: 5724306 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4978. Min Range: -5.4978
Max Act: 5.1228. Min Act: -0.1700
Data Index: 3876873 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19