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

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

Neuron 1028 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4731. Min Act: -0.0001

Data Index: 302962 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.5002. Min Act: -0.0001

Data Index: 87769 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4886. Min Act: -0.0001

Data Index: 1126688 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4360. Min Act: -0.0001

Data Index: 873474 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4469. Min Act: -0.0002

Data Index: 92556 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4036. Min Act: -0.0001

Data Index: 464766 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4186. Min Act: -0.0002

Data Index: 780266 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4393. Min Act: -0.0001

Data Index: 421850 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3503. Min Act: -0.0001

Data Index: 60579 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4739. Min Act: -0.0001

Data Index: 484064 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4334. Min Act: -0.0001

Data Index: 949170 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4180. Min Act: -0.0001

Data Index: 917380 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3841. Min Act: -0.0001

Data Index: 436343 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4192. Min Act: -0.0001

Data Index: 373240 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3671. Min Act: -0.0001

Data Index: 739681 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3951. Min Act: -0.0001

Data Index: 58887 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.4004. Min Act: -0.0001

Data Index: 303354 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3799. Min Act: -0.0001

Data Index: 994131 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3680. Min Act: -0.0001

Data Index: 1327860 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.5002. Min Range: -0.5002

Max Act: 0.3902. Min Act: -0.0001

Data Index: 505876 (C4 (Web Text))

Max Activating Token Index: 605