Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1827 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.4935. Min Act: -0.1700
Data Index: 3774244 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.4623. Min Act: -0.1700
Data Index: 3381353 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.4935. Min Act: -0.1700
Data Index: 2651403 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.4310. Min Act: -0.1700
Data Index: 4205058 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.4623. Min Act: -0.1700
Data Index: 1261369 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.3998. Min Act: -0.1700
Data Index: 7430972 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.4623. Min Act: -0.1700
Data Index: 2125431 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.3685. Min Act: -0.1700
Data Index: 1755002 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.4310. Min Act: -0.1700
Data Index: 412846 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.3998. Min Act: -0.1700
Data Index: 1022205 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.3685. Min Act: -0.1700
Data Index: 1063407 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.2123. Min Act: -0.1700
Data Index: 626689 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.2435. Min Act: -0.1700
Data Index: 6693610 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.0873. Min Act: -0.1700
Data Index: 810133 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4935. Min Range: -6.4935
Max Act: 5.9935. Min Act: -0.1700
Data Index: 2661188 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4935. Min Range: -6.4935
Max Act: 6.0248. Min Act: -0.1700
Data Index: 5279209 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4935. Min Range: -6.4935
Max Act: 5.9935. Min Act: -0.1700
Data Index: 537140 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4935. Min Range: -6.4935
Max Act: 5.9935. Min Act: -0.1700
Data Index: 5173480 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4935. Min Range: -6.4935
Max Act: 5.9310. Min Act: -0.1700
Data Index: 826733 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4935. Min Range: -6.4935
Max Act: 5.8998. Min Act: -0.1700
Data Index: 826734 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19