Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2394 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.7350. Min Act: -0.1700
Data Index: 615378 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.7350. Min Act: -0.1700
Data Index: 57449 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.7350. Min Act: -0.1700
Data Index: 134685 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.7037. Min Act: -0.1700
Data Index: 7114954 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6725. Min Act: -0.1700
Data Index: 6446365 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6725. Min Act: -0.1700
Data Index: 4987576 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6725. Min Act: -0.1700
Data Index: 5705414 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6412. Min Act: -0.1700
Data Index: 3685489 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6100. Min Act: -0.1700
Data Index: 1001484 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6100. Min Act: -0.1700
Data Index: 7177968 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6100. Min Act: -0.1700
Data Index: 2651423 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6100. Min Act: -0.1700
Data Index: 4687517 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5787. Min Act: -0.1700
Data Index: 3185587 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5787. Min Act: -0.1700
Data Index: 5549782 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6100. Min Act: -0.1700
Data Index: 7491150 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5475. Min Act: -0.1700
Data Index: 4083945 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5475. Min Act: -0.1700
Data Index: 1961815 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5475. Min Act: -0.1700
Data Index: 3446708 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5475. Min Act: -0.1700
Data Index: 5110406 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5475. Min Act: -0.1700
Data Index: 1091709 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19