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

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

Neuron 396 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.3790. Min Act: -0.0001

Data Index: 204481 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2755. Min Act: -0.0000

Data Index: 784665 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2874. Min Act: -0.0001

Data Index: 1181842 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1430903 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1241926 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2683. Min Act: -0.0000

Data Index: 23607 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1139266 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2376. Min Act: -0.0001

Data Index: 250318 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1568507 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2377. Min Act: -0.0000

Data Index: 358267 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2313. Min Act: -0.0001

Data Index: 222578 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2387. Min Act: -0.0001

Data Index: 520218 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2166. Min Act: -0.0000

Data Index: 607953 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2177. Min Act: -0.0001

Data Index: 513053 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2413. Min Act: -0.0001

Data Index: 1588206 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2310. Min Act: -0.0000

Data Index: 837248 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2041. Min Act: -0.0000

Data Index: 899935 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2263. Min Act: -0.0000

Data Index: 357322 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2168. Min Act: -0.0001

Data Index: 934681 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.3790. Min Range: -0.3790

Max Act: 0.2090. Min Act: -0.0000

Data Index: 448219 (C4 (Web Text))

Max Activating Token Index: 273