Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 780 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.8555. Min Act: -0.1700
Data Index: 4677289 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.7617. Min Act: -0.1700
Data Index: 7985277 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6680. Min Act: -0.1700
Data Index: 5207562 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6680. Min Act: -0.1700
Data Index: 1740757 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6680. Min Act: -0.1700
Data Index: 2389638 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6680. Min Act: -0.1700
Data Index: 8135164 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6367. Min Act: -0.1700
Data Index: 4493294 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6680. Min Act: -0.1700
Data Index: 5314118 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6055. Min Act: -0.1700
Data Index: 8358638 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6055. Min Act: -0.1700
Data Index: 97929 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6367. Min Act: -0.1700
Data Index: 1084863 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.5742. Min Act: -0.1700
Data Index: 6010865 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.6055. Min Act: -0.1700
Data Index: 2396402 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.5742. Min Act: -0.1700
Data Index: 4671499 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.5742. Min Act: -0.1700
Data Index: 5839891 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.5430. Min Act: -0.1700
Data Index: 4366118 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.5742. Min Act: -0.1700
Data Index: 8040250 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.5117. Min Act: -0.1700
Data Index: 7740465 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.5430. Min Act: -0.1700
Data Index: 7555878 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8555. Min Range: -5.8555
Max Act: 5.5430. Min Act: -0.1700
Data Index: 1204527 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19