Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4803 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.9502. Min Act: -0.1700
Data Index: 5967330 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.8877. Min Act: -0.1700
Data Index: 7101131 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.8877. Min Act: -0.1700
Data Index: 5750824 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.8565. Min Act: -0.1700
Data Index: 4769871 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7940. Min Act: -0.1700
Data Index: 599086 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7627. Min Act: -0.1700
Data Index: 6802409 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7627. Min Act: -0.1700
Data Index: 2433205 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7627. Min Act: -0.1700
Data Index: 4475116 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7627. Min Act: -0.1700
Data Index: 939727 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7315. Min Act: -0.1700
Data Index: 6458115 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7315. Min Act: -0.1700
Data Index: 5750826 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7627. Min Act: -0.1700
Data Index: 2904019 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7002. Min Act: -0.1700
Data Index: 4204937 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7002. Min Act: -0.1696
Data Index: 3477392 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7002. Min Act: -0.1700
Data Index: 6026388 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7002. Min Act: -0.1700
Data Index: 532193 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7002. Min Act: -0.1700
Data Index: 6635661 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7002. Min Act: -0.1700
Data Index: 4710452 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7315. Min Act: -0.1700
Data Index: 5596092 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9502. Min Range: -4.9502
Max Act: 4.7002. Min Act: -0.1700
Data Index: 6701651 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19