Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1827 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.7845. Min Act: -0.1700
Data Index: 619022 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.7328. Min Act: -0.1700
Data Index: 7856679 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.7154. Min Act: -0.1700
Data Index: 8523863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6894. Min Act: -0.1700
Data Index: 3401828 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6547. Min Act: -0.1700
Data Index: 5173837 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6460. Min Act: -0.1700
Data Index: 3546736 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6547. Min Act: -0.1700
Data Index: 6508332 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6286. Min Act: -0.1700
Data Index: 2730238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6286. Min Act: -0.1700
Data Index: 4000088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6286. Min Act: -0.1700
Data Index: 6737858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6286. Min Act: -0.1700
Data Index: 5932712 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6198. Min Act: -0.1700
Data Index: 5276294 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6198. Min Act: -0.1700
Data Index: 6018838 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6111. Min Act: -0.1699
Data Index: 4936944 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6024. Min Act: -0.1700
Data Index: 1292620 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6198. Min Act: -0.1700
Data Index: 961503 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.6024. Min Act: -0.1700
Data Index: 2289036 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.5849. Min Act: -0.1700
Data Index: 7452722 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.5849. Min Act: -0.1698
Data Index: 6000068 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7845. Min Range: -1.7845
Max Act: 1.5762. Min Act: -0.1700
Data Index: 498886 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19