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

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

Neuron 1382 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3073. Min Act: -0.0001

Data Index: 387910 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3251. Min Act: -0.0001

Data Index: 211007 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3097. Min Act: -0.0001

Data Index: 815410 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2951. Min Act: -0.0001

Data Index: 732068 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2579. Min Act: -0.0001

Data Index: 42161 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2585. Min Act: -0.0001

Data Index: 966204 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2554. Min Act: -0.0001

Data Index: 259395 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2468. Min Act: -0.0001

Data Index: 912114 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2457. Min Act: -0.0001

Data Index: 294453 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2425. Min Act: -0.0001

Data Index: 743617 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2329. Min Act: -0.0001

Data Index: 106927 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2477. Min Act: -0.0001

Data Index: 190354 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1137420 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2362. Min Act: -0.0001

Data Index: 285677 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2359. Min Act: -0.0001

Data Index: 43933 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2418. Min Act: -0.0001

Data Index: 264900 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1283964 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2383. Min Act: -0.0001

Data Index: 67042 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2289. Min Act: -0.0001

Data Index: 306011 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2278. Min Act: -0.0001

Data Index: 900074 (C4 (Web Text))

Max Activating Token Index: 727