Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2547 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.3550. Min Act: -0.1700
Data Index: 6051609 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.3080. Min Act: -0.1700
Data Index: 1051195 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.2451. Min Act: -0.1700
Data Index: 5534559 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.2294. Min Act: -0.1700
Data Index: 6942449 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.2137. Min Act: -0.1700
Data Index: 2632324 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.2294. Min Act: -0.1700
Data Index: 4059875 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.2137. Min Act: -0.1700
Data Index: 6510070 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1822. Min Act: -0.1700
Data Index: 1677729 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1822. Min Act: -0.1700
Data Index: 4464914 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1822. Min Act: -0.1700
Data Index: 1925643 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1665. Min Act: -0.1700
Data Index: 754218 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1350. Min Act: -0.1700
Data Index: 7791941 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1508. Min Act: -0.1700
Data Index: 5999415 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1350. Min Act: -0.1700
Data Index: 4112472 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1508. Min Act: -0.1700
Data Index: 749690 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1350. Min Act: -0.1700
Data Index: 513800 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1193. Min Act: -0.1700
Data Index: 5735174 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1193. Min Act: -0.1700
Data Index: 4196673 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.0878. Min Act: -0.1700
Data Index: 546566 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3550. Min Range: -3.3550
Max Act: 3.1035. Min Act: -0.1700
Data Index: 4118790 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19