Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.5897. Min Act: -0.1700
Data Index: 6621128 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.5584. Min Act: -0.1700
Data Index: 3789119 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.5584. Min Act: -0.1700
Data Index: 3463695 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.5272. Min Act: -0.1700
Data Index: 5111543 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.5272. Min Act: -0.1700
Data Index: 8220876 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4959. Min Act: -0.1700
Data Index: 609048 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.5272. Min Act: -0.1700
Data Index: 4334137 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4959. Min Act: -0.1700
Data Index: 6075068 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4959. Min Act: -0.1700
Data Index: 532849 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4959. Min Act: -0.1700
Data Index: 6450604 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4647. Min Act: -0.1700
Data Index: 5289464 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4647. Min Act: -0.1700
Data Index: 7678805 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4647. Min Act: -0.1700
Data Index: 5424374 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4334. Min Act: -0.1700
Data Index: 5900916 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4647. Min Act: -0.1700
Data Index: 4793458 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4334. Min Act: -0.1700
Data Index: 7301360 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4334. Min Act: -0.1700
Data Index: 6621592 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4021. Min Act: -0.1700
Data Index: 4443402 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4647. Min Act: -0.1700
Data Index: 8256748 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5897. Min Range: -4.5897
Max Act: 4.4021. Min Act: -0.1700
Data Index: 6367609 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19