Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 822 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4940. Min Act: 0.0001

Data Index: 1147204 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.5004. Min Act: -0.0000

Data Index: 916245 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4505. Min Act: -0.0001

Data Index: 916038 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4508. Min Act: 0.0001

Data Index: 729956 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4546. Min Act: -0.0001

Data Index: 545600 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4512. Min Act: -0.0001

Data Index: 1244474 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4214. Min Act: -0.0000

Data Index: 277418 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4111. Min Act: -0.0001

Data Index: 1062435 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4312. Min Act: -0.0001

Data Index: 209790 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4098. Min Act: -0.0001

Data Index: 1359310 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4223. Min Act: -0.0001

Data Index: 399478 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4186. Min Act: -0.0000

Data Index: 345389 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4038. Min Act: -0.0001

Data Index: 73718 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4279. Min Act: 0.0001

Data Index: 1136504 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3939. Min Act: 0.0000

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4089. Min Act: -0.0001

Data Index: 546915 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4034. Min Act: 0.0001

Data Index: 907303 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4011. Min Act: -0.0000

Data Index: 649313 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3911. Min Act: -0.0001

Data Index: 178882 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3823. Min Act: -0.0001

Data Index: 723161 (C4 (Web Text))

Max Activating Token Index: 117