Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.2295. Min Act: -0.1700
Data Index: 6609338 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.2607. Min Act: -0.1700
Data Index: 2813818 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.2607. Min Act: -0.1700
Data Index: 5725787 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.2607. Min Act: -0.1700
Data Index: 1119411 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.2295. Min Act: -0.1700
Data Index: 2788708 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.2295. Min Act: -0.1700
Data Index: 5387884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1982. Min Act: -0.1700
Data Index: 1119407 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1982. Min Act: -0.1700
Data Index: 3625130 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1982. Min Act: -0.1700
Data Index: 7158 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1670. Min Act: -0.1700
Data Index: 2760595 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1357. Min Act: -0.1700
Data Index: 6250847 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1670. Min Act: -0.1700
Data Index: 824274 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1670. Min Act: -0.1700
Data Index: 8451078 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1670. Min Act: -0.1700
Data Index: 7678628 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1357. Min Act: -0.1700
Data Index: 3923317 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1357. Min Act: -0.1700
Data Index: 1119409 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1357. Min Act: -0.1700
Data Index: 385639 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1045. Min Act: -0.1700
Data Index: 72438 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1357. Min Act: -0.1700
Data Index: 2832826 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2607. Min Range: -5.2607
Max Act: 5.1357. Min Act: -0.1700
Data Index: 1215045 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19