Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 902 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.2493. Min Act: -0.1700
Data Index: 6080938 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.2180. Min Act: -0.1700
Data Index: 6686579 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1868. Min Act: -0.1700
Data Index: 5367370 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 2291546 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1868. Min Act: -0.1700
Data Index: 5028176 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1868. Min Act: -0.1700
Data Index: 2990890 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1868. Min Act: -0.1700
Data Index: 2908021 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1868. Min Act: -0.1700
Data Index: 7613430 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 8476641 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 8401333 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 3235100 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 2206785 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1243. Min Act: -0.1700
Data Index: 2028516 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1243. Min Act: -0.1700
Data Index: 7835093 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 5176503 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 6814756 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 4965821 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1698
Data Index: 6178923 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 4011232 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2493. Min Range: -6.2493
Max Act: 6.1555. Min Act: -0.1700
Data Index: 5641588 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19