Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4366 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0579. Min Range: -4.0579
Max Act: 4.0579. Min Act: -0.1700
Data Index: 1989834 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0579. Min Range: -4.0579
Max Act: 4.0579. Min Act: -0.1700
Data Index: 2549851 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0579. Min Range: -4.0579
Max Act: 4.0266. Min Act: -0.1700
Data Index: 8565219 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9016. Min Act: -0.1700
Data Index: 22959 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9016. Min Act: -0.1700
Data Index: 3393911 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.8860. Min Act: -0.1700
Data Index: 5295813 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.8860. Min Act: -0.1700
Data Index: 5829151 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.8547. Min Act: -0.1700
Data Index: 6673244 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.8547. Min Act: -0.1700
Data Index: 3556156 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.8703. Min Act: -0.1700
Data Index: 5752840 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.8391. Min Act: -0.1700
Data Index: 655827 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.8391. Min Act: -0.1700
Data Index: 573404 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.8078. Min Act: -0.1700
Data Index: 8636486 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.7921. Min Act: -0.1700
Data Index: 7376525 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.7765. Min Act: -0.1700
Data Index: 8467811 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.7765. Min Act: -0.1700
Data Index: 5135315 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.7609. Min Act: -0.1700
Data Index: 4430850 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.7765. Min Act: -0.1700
Data Index: 1389839 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.7452. Min Act: -0.1700
Data Index: 2735694 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.7609. Min Act: -0.1700
Data Index: 8526292 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19