Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.6089. Min Act: -0.1700
Data Index: 3629239 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.5777. Min Act: -0.1700
Data Index: 7930878 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.5464. Min Act: -0.1700
Data Index: 7046458 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.4527. Min Act: -0.1700
Data Index: 8479939 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.4214. Min Act: -0.1700
Data Index: 8761743 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.3589. Min Act: -0.1700
Data Index: 5442672 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.3902. Min Act: -0.1700
Data Index: 3443650 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.3902. Min Act: -0.1700
Data Index: 2892647 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.3902. Min Act: -0.1700
Data Index: 4992373 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.3589. Min Act: -0.1700
Data Index: 5002953 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.3277. Min Act: -0.1700
Data Index: 1148692 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2964. Min Act: -0.1700
Data Index: 5023604 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2964. Min Act: -0.1700
Data Index: 2704501 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2652. Min Act: -0.1700
Data Index: 6083493 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2339. Min Act: -0.1700
Data Index: 3993410 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2339. Min Act: -0.1700
Data Index: 6961057 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2339. Min Act: -0.1700
Data Index: 3629241 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2027. Min Act: -0.1700
Data Index: 646662 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2027. Min Act: -0.1700
Data Index: 849074 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6089. Min Range: -4.6089
Max Act: 4.2027. Min Act: -0.1700
Data Index: 2533724 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19