Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5793 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.7269. Min Act: -0.0000

Data Index: 164886 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.7723. Min Act: -0.0000

Data Index: 1080532 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.8093. Min Act: -0.0001

Data Index: 1040565 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.6423. Min Act: -0.0001

Data Index: 1274754 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.6253. Min Act: -0.0001

Data Index: 1143128 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.6835. Min Act: -0.0001

Data Index: 21368 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.5835. Min Act: -0.0001

Data Index: 365666 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.5226. Min Act: -0.0001

Data Index: 805647 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.7941. Min Act: -0.0001

Data Index: 764378 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.6310. Min Act: -0.0001

Data Index: 63400 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.6076. Min Act: -0.0001

Data Index: 186626 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.4456. Min Act: -0.0001

Data Index: 586136 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.5977. Min Act: -0.0001

Data Index: 584998 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.4976. Min Act: -0.0001

Data Index: 438919 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.5246. Min Act: -0.0001

Data Index: 475790 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.5231. Min Act: -0.0001

Data Index: 1302494 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.3398. Min Act: -0.0001

Data Index: 529487 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.4918. Min Act: -0.0001

Data Index: 51285 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.4172. Min Act: -0.0000

Data Index: 341375 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 1.8093. Min Range: -1.8093

Max Act: 1.5551. Min Act: -0.0001

Data Index: 58025 (C4 (Web Text))

Max Activating Token Index: 765