Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 131 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1872. Min Range: -2.1872

Max Act: 2.1872. Min Act: -0.0000

Data Index: 1088431 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 2.1872. Min Range: -2.1872

Max Act: 2.0084. Min Act: -0.0000

Data Index: 711940 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.7862. Min Act: -0.0000

Data Index: 878898 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1124407 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.5006. Min Act: -0.0000

Data Index: 1060140 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.4263. Min Act: -0.0000

Data Index: 545201 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.3223. Min Act: -0.0000

Data Index: 1148987 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2148. Min Act: -0.0000

Data Index: 311070 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2705. Min Act: -0.0000

Data Index: 239165 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.3201. Min Act: -0.0000

Data Index: 350559 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.1244. Min Act: -0.0000

Data Index: 791779 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2552. Min Act: -0.0000

Data Index: 454505 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.3722. Min Act: -0.0000

Data Index: 946076 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2365. Min Act: -0.0000

Data Index: 1115860 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1571620 (Python Code)

Max Activating Token Index: 890

Text #15

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1409503 (Python Code)

Max Activating Token Index: 526

Text #16

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.1138. Min Act: -0.0000

Data Index: 128073 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2198. Min Act: -0.0000

Data Index: 367933 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1148159 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 2.1872. Min Range: -2.1872

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1324360 (C4 (Web Text))

Max Activating Token Index: 567