Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4023 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.4835. Min Act: -0.1700
Data Index: 5074616 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.4521. Min Act: -0.1700
Data Index: 4138042 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.3267. Min Act: -0.1700
Data Index: 4913220 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2639. Min Act: -0.1700
Data Index: 1883630 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2639. Min Act: -0.1700
Data Index: 8078944 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2325. Min Act: -0.1700
Data Index: 6186045 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2167. Min Act: -0.1700
Data Index: 503447 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2639. Min Act: -0.1700
Data Index: 1521835 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2325. Min Act: -0.1700
Data Index: 1002812 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2325. Min Act: -0.1700
Data Index: 3410616 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2639. Min Act: -0.1700
Data Index: 129877 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2167. Min Act: -0.1700
Data Index: 5072720 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.2010. Min Act: -0.1700
Data Index: 8693111 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.1853. Min Act: -0.1700
Data Index: 8524625 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.1853. Min Act: -0.1700
Data Index: 1557301 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.1538. Min Act: -0.1700
Data Index: 200092 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.1696. Min Act: -0.1700
Data Index: 5357503 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.1696. Min Act: -0.1700
Data Index: 8315594 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.1696. Min Act: -0.1700
Data Index: 7363998 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4835. Min Range: -3.4835
Max Act: 3.1538. Min Act: -0.1700
Data Index: 4296136 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19