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

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

Neuron 1616 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: 1.4729. Min Range: -1.4729

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1395361 (Python Code)

Max Activating Token Index: 939

Text #1

Max Range: 1.4729. Min Range: -1.4729

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1548143 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 1.4729. Min Range: -1.4729

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1334652 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 1.4729. Min Range: -1.4729

Max Act: 1.1238. Min Act: -0.0000

Data Index: 924568 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.4729. Min Range: -1.4729

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1583473 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 1.4729. Min Range: -1.4729

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1608446 (Python Code)

Max Activating Token Index: 656

Text #6

Max Range: 1.4729. Min Range: -1.4729

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1405082 (Python Code)

Max Activating Token Index: 683

Text #7

Max Range: 1.4729. Min Range: -1.4729

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1452378 (Python Code)

Max Activating Token Index: 916

Text #8

Max Range: 1.4729. Min Range: -1.4729

Max Act: 1.0046. Min Act: 0.0000

Data Index: 1644663 (Python Code)

Max Activating Token Index: 973

Text #9

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.9697. Min Act: -0.0000

Data Index: 523508 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1592974 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1578740 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1541732 (Python Code)

Max Activating Token Index: 727

Text #13

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1384138 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1458100 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1471789 (Python Code)

Max Activating Token Index: 238

Text #16

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.8524. Min Act: -0.0000

Data Index: 983027 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1050279 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.8471. Min Act: -0.0000

Data Index: 428304 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 1.4729. Min Range: -1.4729

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1441913 (Python Code)

Max Activating Token Index: 443