Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2684. Min Range: -7.2684
Max Act: 7.2684. Min Act: -0.1700
Data Index: 6857465 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2684. Min Range: -7.2684
Max Act: 7.2372. Min Act: -0.1700
Data Index: 3631487 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2684. Min Range: -7.2684
Max Act: 7.0497. Min Act: -0.1700
Data Index: 8160727 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.7684. Min Act: -0.1700
Data Index: 3036305 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.7059. Min Act: -0.1700
Data Index: 7775132 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.7059. Min Act: -0.1700
Data Index: 520060 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.7372. Min Act: -0.1700
Data Index: 1727027 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.6747. Min Act: -0.1700
Data Index: 48832 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.6434. Min Act: -0.1700
Data Index: 984493 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.6434. Min Act: -0.1700
Data Index: 5705445 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.6122. Min Act: -0.1700
Data Index: 1285900 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.6122. Min Act: -0.1700
Data Index: 2550713 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.6122. Min Act: -0.1700
Data Index: 1953337 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.6122. Min Act: -0.1700
Data Index: 5135590 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.5809. Min Act: -0.1700
Data Index: 8415181 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.5809. Min Act: -0.1700
Data Index: 4781908 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.5809. Min Act: -0.1700
Data Index: 7268213 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.5497. Min Act: -0.1700
Data Index: 1311555 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.5497. Min Act: -0.1700
Data Index: 6594733 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2684. Min Range: -7.2684
Max Act: 6.5497. Min Act: -0.1700
Data Index: 8811607 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19