Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2627 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.7181. Min Act: -0.1700
Data Index: 3965200 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.7181. Min Act: -0.1700
Data Index: 3084047 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.7493. Min Act: -0.1700
Data Index: 5528519 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.7493. Min Act: -0.1700
Data Index: 2418781 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.6868. Min Act: -0.1700
Data Index: 6378702 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.6868. Min Act: -0.1700
Data Index: 4795684 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.6868. Min Act: -0.1700
Data Index: 6839134 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.6868. Min Act: -0.1700
Data Index: 3914782 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.6868. Min Act: -0.1700
Data Index: 2904485 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.6556. Min Act: -0.1700
Data Index: 3010113 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.6868. Min Act: -0.1700
Data Index: 8507638 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.6556. Min Act: -0.1700
Data Index: 4863850 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.5931. Min Act: -0.1700
Data Index: 3806345 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.5931. Min Act: -0.1700
Data Index: 3051035 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.5931. Min Act: -0.1700
Data Index: 6455393 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.5931. Min Act: -0.1700
Data Index: 2641314 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.5306. Min Act: -0.1700
Data Index: 5661967 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.5618. Min Act: -0.1700
Data Index: 3809541 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.5618. Min Act: -0.1700
Data Index: 2711146 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7493. Min Range: -4.7493
Max Act: 4.5618. Min Act: -0.1700
Data Index: 498496 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19