Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3235 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3488. Min Act: -0.0002

Data Index: 1140274 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3519. Min Act: -0.0002

Data Index: 164683 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3455. Min Act: -0.0001

Data Index: 713401 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3319. Min Act: -0.0001

Data Index: 550835 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3296. Min Act: -0.0002

Data Index: 1073867 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3360. Min Act: -0.0002

Data Index: 1316420 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3258. Min Act: -0.0002

Data Index: 1205280 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3146. Min Act: -0.0001

Data Index: 558620 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3481. Min Act: -0.0001

Data Index: 620650 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3050. Min Act: -0.0002

Data Index: 921022 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3195. Min Act: -0.0001

Data Index: 1281961 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3265. Min Act: -0.0002

Data Index: 657588 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3196. Min Act: -0.0002

Data Index: 1314052 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3088. Min Act: -0.0001

Data Index: 41097 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2909. Min Act: -0.0002

Data Index: 491396 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3168. Min Act: -0.0002

Data Index: 593059 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2742. Min Act: -0.0001

Data Index: 212144 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.2942. Min Act: -0.0001

Data Index: 550277 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3014. Min Act: -0.0002

Data Index: 1075119 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.3519. Min Range: -0.3519

Max Act: 0.3294. Min Act: -0.0002

Data Index: 1109502 (C4 (Web Text))

Max Activating Token Index: 142