Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4570 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.6571. Min Act: -0.1700
Data Index: 2846801 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.6101. Min Act: -0.1700
Data Index: 6613468 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.6258. Min Act: -0.1700
Data Index: 841568 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5945. Min Act: -0.1700
Data Index: 129881 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5006. Min Act: -0.1700
Data Index: 1938416 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4849. Min Act: -0.1700
Data Index: 3234657 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4849. Min Act: -0.1700
Data Index: 4086068 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4849. Min Act: -0.1700
Data Index: 1852826 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4849. Min Act: -0.1700
Data Index: 1582599 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4692. Min Act: -0.1700
Data Index: 5097851 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4692. Min Act: -0.1700
Data Index: 5649753 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4536. Min Act: -0.1700
Data Index: 4387488 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4536. Min Act: -0.1700
Data Index: 2639438 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4379. Min Act: -0.1700
Data Index: 5300590 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4536. Min Act: -0.1700
Data Index: 7063567 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4536. Min Act: -0.1700
Data Index: 4700928 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4379. Min Act: -0.1700
Data Index: 4745388 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4379. Min Act: -0.1700
Data Index: 6857351 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4222. Min Act: -0.1700
Data Index: 4943373 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4065. Min Act: -0.1700
Data Index: 1570302 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19