Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.6481. Min Act: -0.1700
Data Index: 3999924 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.5231. Min Act: -0.1700
Data Index: 1729202 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 4984101 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 6127368 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 1593208 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 5431182 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3356. Min Act: -0.1700
Data Index: 899476 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.3356. Min Act: -0.1700
Data Index: 5075665 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 4762851 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 4672500 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 5238930 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 3331174 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 5181967 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2731. Min Act: -0.1700
Data Index: 2748459 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2106. Min Act: -0.1700
Data Index: 6079262 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2106. Min Act: -0.1700
Data Index: 3209588 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2106. Min Act: -0.1700
Data Index: 8401414 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2106. Min Act: -0.1700
Data Index: 649325 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.2106. Min Act: -0.1700
Data Index: 326425 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6481. Min Range: -8.6481
Max Act: 8.1481. Min Act: -0.1700
Data Index: 3767641 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19