Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1515 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.4637. Min Act: -0.1700
Data Index: 7426253 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.4324. Min Act: -0.1700
Data Index: 2603435 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.4167. Min Act: -0.1700
Data Index: 5350291 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.4167. Min Act: -0.1700
Data Index: 13415 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.4167. Min Act: -0.1700
Data Index: 6061549 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.4010. Min Act: -0.1700
Data Index: 2928598 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.4167. Min Act: -0.1700
Data Index: 3580765 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.4010. Min Act: -0.1700
Data Index: 8733895 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3697. Min Act: -0.1700
Data Index: 7144963 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3540. Min Act: -0.1700
Data Index: 1159369 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3540. Min Act: -0.1700
Data Index: 4496321 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3383. Min Act: -0.1700
Data Index: 8123826 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3383. Min Act: -0.1700
Data Index: 7705885 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3383. Min Act: -0.1700
Data Index: 5352862 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3383. Min Act: -0.1700
Data Index: 527264 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3383. Min Act: -0.1700
Data Index: 5989627 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3383. Min Act: -0.1700
Data Index: 4970989 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3226. Min Act: -0.1700
Data Index: 3025756 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.2912. Min Act: -0.1700
Data Index: 6622648 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4637. Min Range: -3.4637
Max Act: 3.3069. Min Act: -0.1700
Data Index: 8095632 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19