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

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

Neuron 1984 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1211856 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1033609 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3867. Min Act: -0.0000

Data Index: 975360 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3711. Min Act: -0.0000

Data Index: 278593 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1221670 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3726. Min Act: -0.0000

Data Index: 476193 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3234. Min Act: -0.0000

Data Index: 981652 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3424. Min Act: -0.0000

Data Index: 717873 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3319. Min Act: -0.0000

Data Index: 919704 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3362. Min Act: -0.0000

Data Index: 241588 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3389. Min Act: -0.0000

Data Index: 573938 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3455. Min Act: -0.0000

Data Index: 822762 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1250844 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3280. Min Act: -0.0000

Data Index: 406115 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3240. Min Act: -0.0000

Data Index: 204707 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3261. Min Act: -0.0000

Data Index: 590267 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1171055 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.2956. Min Act: -0.0000

Data Index: 268003 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3250. Min Act: -0.0000

Data Index: 597594 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.4065. Min Range: -0.4065

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1226439 (C4 (Web Text))

Max Activating Token Index: 607