Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1182 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.5475. Min Act: -0.1700
Data Index: 1511253 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.5632. Min Act: -0.1700
Data Index: 2376426 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.3595. Min Act: -0.1700
Data Index: 7830496 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.2496. Min Act: -0.1700
Data Index: 1427052 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.2653. Min Act: -0.1700
Data Index: 7802705 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.1867. Min Act: -0.1700
Data Index: 546493 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.1080. Min Act: -0.1700
Data Index: 8563537 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.1080. Min Act: -0.1700
Data Index: 4741351 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.1080. Min Act: -0.1700
Data Index: 2699573 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0449. Min Act: -0.1700
Data Index: 1500896 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0607. Min Act: -0.1700
Data Index: 8573576 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0607. Min Act: -0.1700
Data Index: 3565629 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0607. Min Act: -0.1700
Data Index: 5820237 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0449. Min Act: -0.1700
Data Index: 3834752 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0292. Min Act: -0.1700
Data Index: 4448742 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0292. Min Act: -0.1700
Data Index: 4714293 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0292. Min Act: -0.1700
Data Index: 1248568 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5632. Min Range: -3.5632
Max Act: 2.9976. Min Act: -0.1700
Data Index: 6994748 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0134. Min Act: -0.1700
Data Index: 7576375 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5632. Min Range: -3.5632
Max Act: 3.0134. Min Act: -0.1700
Data Index: 8539332 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19