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

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

Neuron 60 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1573575 (Python Code)

Max Activating Token Index: 875

Text #1

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.5985. Min Act: -0.0000

Data Index: 1536186 (Python Code)

Max Activating Token Index: 783

Text #2

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2696. Min Act: -0.0000

Data Index: 1415720 (Python Code)

Max Activating Token Index: 779

Text #3

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1370241 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1635638 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1552139 (Python Code)

Max Activating Token Index: 716

Text #6

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1565839 (Python Code)

Max Activating Token Index: 249

Text #7

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1520008 (Python Code)

Max Activating Token Index: 745

Text #8

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1637662 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1503621 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 1.5985. Min Range: -1.5985

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1594356 (Python Code)

Max Activating Token Index: 960

Text #11

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1546530 (Python Code)

Max Activating Token Index: 877

Text #12

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1521205 (Python Code)

Max Activating Token Index: 524

Text #13

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9394. Min Act: -0.0000

Data Index: 668218 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1440410 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1514197 (Python Code)

Max Activating Token Index: 317

Text #16

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9295. Min Act: 0.0000

Data Index: 1517390 (Python Code)

Max Activating Token Index: 366

Text #17

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1525110 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1369407 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 1.5985. Min Range: -1.5985

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1537336 (Python Code)

Max Activating Token Index: 202