Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.3600. Min Act: -0.1700
Data Index: 107035 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.2350. Min Act: -0.1700
Data Index: 5626643 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.2037. Min Act: -0.1700
Data Index: 6805043 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.1725. Min Act: -0.1700
Data Index: 6456428 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.1725. Min Act: -0.1700
Data Index: 5898371 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.1725. Min Act: -0.1700
Data Index: 5091708 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.1100. Min Act: -0.1700
Data Index: 5626632 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.1100. Min Act: -0.1700
Data Index: 5728918 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.1100. Min Act: -0.1700
Data Index: 492528 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.1100. Min Act: -0.1700
Data Index: 5626638 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0787. Min Act: -0.1700
Data Index: 5947201 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0787. Min Act: -0.1700
Data Index: 2562982 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0475. Min Act: -0.1700
Data Index: 1628438 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0787. Min Act: -0.1700
Data Index: 931974 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0787. Min Act: -0.1700
Data Index: 5728911 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0787. Min Act: -0.1700
Data Index: 5728913 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0475. Min Act: -0.1700
Data Index: 1816327 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0475. Min Act: -0.1700
Data Index: 1003978 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0162. Min Act: -0.1700
Data Index: 5737070 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3600. Min Range: -6.3600
Max Act: 6.0162. Min Act: -0.1700
Data Index: 4592983 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19