Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.5066. Min Act: -0.1700
Data Index: 1116621 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.4596. Min Act: -0.1700
Data Index: 7977124 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.3812. Min Act: -0.1700
Data Index: 5633392 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.4126. Min Act: -0.1700
Data Index: 8680506 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.3812. Min Act: -0.1700
Data Index: 7845982 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.3812. Min Act: -0.1700
Data Index: 3876087 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.3185. Min Act: -0.1700
Data Index: 444529 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2871. Min Act: -0.1700
Data Index: 924857 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.3028. Min Act: -0.1700
Data Index: 6808698 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.3028. Min Act: -0.1700
Data Index: 417114 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2871. Min Act: -0.1700
Data Index: 1730346 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2714. Min Act: -0.1700
Data Index: 6711678 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2714. Min Act: -0.1700
Data Index: 7591622 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2557. Min Act: -0.1700
Data Index: 6838632 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2557. Min Act: -0.1700
Data Index: 3651608 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2714. Min Act: -0.1700
Data Index: 5075084 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2714. Min Act: -0.1700
Data Index: 4555241 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2714. Min Act: -0.1700
Data Index: 1049027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2714. Min Act: -0.1700
Data Index: 182746 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5066. Min Range: -3.5066
Max Act: 3.2399. Min Act: -0.1700
Data Index: 2345616 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19