Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1054. Min Range: -5.1054
Max Act: 5.1054. Min Act: -0.1700
Data Index: 4703035 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9804. Min Act: -0.1700
Data Index: 8275658 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9491. Min Act: -0.1700
Data Index: 2110586 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.9491. Min Act: -0.1700
Data Index: 3806149 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8866. Min Act: -0.1700
Data Index: 2232415 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.8554. Min Act: -0.1700
Data Index: 4145808 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.7929. Min Act: -0.1700
Data Index: 3858321 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.7616. Min Act: -0.1700
Data Index: 5059719 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.7929. Min Act: -0.1700
Data Index: 5262875 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.7616. Min Act: -0.1700
Data Index: 2020755 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.7304. Min Act: -0.1700
Data Index: 4106165 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.6991. Min Act: -0.1700
Data Index: 4621590 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.6991. Min Act: -0.1700
Data Index: 4406416 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.6991. Min Act: -0.1700
Data Index: 7410810 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.6991. Min Act: -0.1700
Data Index: 5825725 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.7304. Min Act: -0.1700
Data Index: 3392500 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.6991. Min Act: -0.1700
Data Index: 2782827 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.6991. Min Act: -0.1700
Data Index: 5257476 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.6991. Min Act: -0.1700
Data Index: 2700792 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1054. Min Range: -5.1054
Max Act: 4.6991. Min Act: -0.1700
Data Index: 1634257 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19