Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.6689. Min Act: -0.1700
Data Index: 7542410 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.7939. Min Act: -0.1700
Data Index: 4464184 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1064. Min Range: -11.1064
Max Act: 11.1064. Min Act: -0.1700
Data Index: 4157941 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.3564. Min Act: -0.1700
Data Index: 6767657 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.2939. Min Act: -0.1700
Data Index: 3736125 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.0439. Min Act: -0.1700
Data Index: 4614024 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1064. Min Range: -11.1064
Max Act: 9.9814. Min Act: -0.1700
Data Index: 7470807 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.3564. Min Act: -0.1700
Data Index: 5605688 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.1064. Min Act: -0.1700
Data Index: 2574041 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.0439. Min Act: -0.1700
Data Index: 6307423 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.0439. Min Act: -0.1700
Data Index: 5812670 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.0439. Min Act: -0.1700
Data Index: 7748672 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.1689. Min Act: -0.1700
Data Index: 8464410 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1064. Min Range: -11.1064
Max Act: 9.7314. Min Act: -0.1700
Data Index: 888171 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.2314. Min Act: -0.1700
Data Index: 1467504 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.1064. Min Act: -0.1700
Data Index: 718408 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1064. Min Range: -11.1064
Max Act: 9.4814. Min Act: -0.1700
Data Index: 2462793 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.0439. Min Act: -0.1700
Data Index: 303464 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1064. Min Range: -11.1064
Max Act: 9.6064. Min Act: -0.1700
Data Index: 961875 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1064. Min Range: -11.1064
Max Act: 10.0439. Min Act: -0.1700
Data Index: 5348616 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19