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

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

Neuron 4138 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0001

Data Index: 118091 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1751. Min Act: -0.0001

Data Index: 227006 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1805. Min Act: -0.0001

Data Index: 209096 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1483. Min Act: -0.0001

Data Index: 498825 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1484. Min Act: -0.0001

Data Index: 326551 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1352. Min Act: -0.0001

Data Index: 548718 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1165107 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1229. Min Act: -0.0001

Data Index: 135442 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1196. Min Act: -0.0001

Data Index: 307046 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1006. Min Act: -0.0001

Data Index: 740510 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1291. Min Act: -0.0001

Data Index: 777109 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1350. Min Act: -0.0001

Data Index: 161738 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1452958 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1220. Min Act: -0.0001

Data Index: 663370 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1301225 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1244. Min Act: -0.0001

Data Index: 965246 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1256063 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1297529 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1173520 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1483495 (Python Code)

Max Activating Token Index: 76