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

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

Neuron 4330 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.5959. Min Act: -0.0001

Data Index: 215417 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.5399. Min Act: -0.0000

Data Index: 23683 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.3609. Min Act: -0.0000

Data Index: 238255 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.2321. Min Act: -0.0000

Data Index: 1653482 (Python Code)

Max Activating Token Index: 947

Text #4

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.3523. Min Act: -0.0000

Data Index: 1307067 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.3421. Min Act: -0.0000

Data Index: 337621 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.3231. Min Act: -0.0000

Data Index: 695588 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.3296. Min Act: -0.0000

Data Index: 1329544 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.2910. Min Act: -0.0000

Data Index: 1335514 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.2846. Min Act: -0.0000

Data Index: 411213 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.1504. Min Act: -0.0000

Data Index: 158108 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.2420. Min Act: -0.0000

Data Index: 212639 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.2227. Min Act: -0.0000

Data Index: 388871 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.2224. Min Act: -0.0001

Data Index: 1312769 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.1850. Min Act: -0.0000

Data Index: 780857 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.1839. Min Act: -0.0000

Data Index: 984868 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.3024. Min Act: -0.0000

Data Index: 1228397 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.2792. Min Act: -0.0000

Data Index: 511481 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.1461. Min Act: -0.0000

Data Index: 468206 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 2.5959. Min Range: -2.5959

Max Act: 2.1299. Min Act: -0.0000

Data Index: 1254752 (C4 (Web Text))

Max Activating Token Index: 289