Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5096 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.5939. Min Act: -0.1700
Data Index: 310307 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.3751. Min Act: -0.1700
Data Index: 6888533 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.2501. Min Act: -0.1700
Data Index: 4217574 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.2501. Min Act: -0.1700
Data Index: 7755557 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.2501. Min Act: -0.1700
Data Index: 8106486 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.1564. Min Act: -0.1700
Data Index: 6414219 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.1251. Min Act: -0.1700
Data Index: 1517231 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.1251. Min Act: -0.1700
Data Index: 8522189 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0939. Min Act: -0.1700
Data Index: 7453485 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0939. Min Act: -0.1700
Data Index: 1409225 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0939. Min Act: -0.1700
Data Index: 1135185 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0939. Min Act: -0.1700
Data Index: 5183296 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0939. Min Act: -0.1700
Data Index: 1549989 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0626. Min Act: -0.1700
Data Index: 2537419 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6457974 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0314. Min Act: -0.1700
Data Index: 1152495 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0314. Min Act: -0.1700
Data Index: 7981096 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.0001. Min Act: -0.1700
Data Index: 4660323 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.9689. Min Act: -0.1700
Data Index: 3213853 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.9689. Min Act: -0.1700
Data Index: 742468 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19