Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3697 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.7405. Min Act: -0.1700
Data Index: 6641069 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6780. Min Act: -0.1700
Data Index: 4381866 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6936. Min Act: -0.1700
Data Index: 3142718 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6467. Min Act: -0.1700
Data Index: 5037867 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6623. Min Act: -0.1700
Data Index: 4223396 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6310. Min Act: -0.1700
Data Index: 2818568 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6154. Min Act: -0.1700
Data Index: 4381864 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6467. Min Act: -0.1700
Data Index: 388992 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6310. Min Act: -0.1700
Data Index: 6257024 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6310. Min Act: -0.1700
Data Index: 4933997 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.6310. Min Act: -0.1700
Data Index: 1008679 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5997. Min Act: -0.1700
Data Index: 8376460 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5841. Min Act: -0.1700
Data Index: 6036955 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5997. Min Act: -0.1700
Data Index: 4505926 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5841. Min Act: -0.1700
Data Index: 3567024 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5997. Min Act: -0.1700
Data Index: 8318910 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5841. Min Act: -0.1700
Data Index: 7364466 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5841. Min Act: -0.1700
Data Index: 4103804 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5997. Min Act: -0.1700
Data Index: 98263 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7405. Min Range: -3.7405
Max Act: 3.5684. Min Act: -0.1700
Data Index: 3880958 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19