Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2347 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.5133. Min Act: -0.0001

Data Index: 1389589 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.4045. Min Act: -0.0001

Data Index: 707553 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.2617. Min Act: -0.0001

Data Index: 1395125 (Python Code)

Max Activating Token Index: 234

Text #3

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.1319. Min Act: -0.0001

Data Index: 477650 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.1479. Min Act: -0.0001

Data Index: 162188 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.0805. Min Act: -0.0001

Data Index: 572625 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.5133. Min Range: -1.5133

Max Act: 1.0465. Min Act: -0.0001

Data Index: 1019227 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.9747. Min Act: -0.0001

Data Index: 282036 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.9534. Min Act: -0.0001

Data Index: 1347755 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.9183. Min Act: -0.0001

Data Index: 1483107 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.8631. Min Act: -0.0001

Data Index: 1294559 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.8933. Min Act: -0.0001

Data Index: 369462 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1627375 (Python Code)

Max Activating Token Index: 316

Text #13

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.8420. Min Act: -0.0001

Data Index: 1069986 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.8761. Min Act: -0.0001

Data Index: 1064248 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.9168. Min Act: -0.0001

Data Index: 1422065 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.9106. Min Act: -0.0001

Data Index: 1085830 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.8366. Min Act: -0.0001

Data Index: 1645088 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.8746. Min Act: -0.0001

Data Index: 647706 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 1.5133. Min Range: -1.5133

Max Act: 0.8413. Min Act: -0.0001

Data Index: 749754 (C4 (Web Text))

Max Activating Token Index: 43