Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.2387. Min Act: -0.1700
Data Index: 4344499 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.2074. Min Act: -0.1700
Data Index: 8301803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.2074. Min Act: -0.1700
Data Index: 2575836 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1762. Min Act: -0.1700
Data Index: 3029394 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1449. Min Act: -0.1700
Data Index: 7350999 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1449. Min Act: -0.1700
Data Index: 7830753 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1449. Min Act: -0.1700
Data Index: 8042555 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1449. Min Act: -0.1700
Data Index: 1961275 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1137. Min Act: -0.1700
Data Index: 5830616 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1137. Min Act: -0.1700
Data Index: 1419077 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1449. Min Act: -0.1700
Data Index: 8439546 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.1137. Min Act: -0.1700
Data Index: 2754813 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.0512. Min Act: -0.1700
Data Index: 4115506 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.0824. Min Act: -0.1700
Data Index: 3609822 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.0824. Min Act: -0.1700
Data Index: 4516710 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.0824. Min Act: -0.1700
Data Index: 4547198 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.0824. Min Act: -0.1700
Data Index: 4674360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.0824. Min Act: -0.1700
Data Index: 1843288 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.0824. Min Act: -0.1700
Data Index: 5231406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2387. Min Range: -5.2387
Max Act: 5.0824. Min Act: -0.1700
Data Index: 5779554 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19