Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.9835. Min Act: -0.1700
Data Index: 4523899 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.9210. Min Act: -0.1700
Data Index: 3258171 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.8272. Min Act: -0.1700
Data Index: 5564240 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.8272. Min Act: -0.1700
Data Index: 1286183 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.7335. Min Act: -0.1700
Data Index: 858018 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.7022. Min Act: -0.1700
Data Index: 4535778 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6710. Min Act: -0.1700
Data Index: 6822716 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.7335. Min Act: -0.1700
Data Index: 688862 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6397. Min Act: -0.1700
Data Index: 6178987 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6710. Min Act: -0.1700
Data Index: 4988383 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.7022. Min Act: -0.1700
Data Index: 637126 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6710. Min Act: -0.1700
Data Index: 367951 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6710. Min Act: -0.1700
Data Index: 2150702 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6710. Min Act: -0.1700
Data Index: 4397643 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6085. Min Act: -0.1700
Data Index: 4259675 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6085. Min Act: -0.1700
Data Index: 7305970 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6397. Min Act: -0.1700
Data Index: 717749 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.6085. Min Act: -0.1700
Data Index: 7103111 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.5460. Min Act: -0.1700
Data Index: 1460732 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9835. Min Range: -4.9835
Max Act: 4.5460. Min Act: -0.1700
Data Index: 5110837 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19