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

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

Neuron 423 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.7374. Min Act: -0.0001

Data Index: 633763 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.0924. Min Act: -0.0001

Data Index: 177650 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.1192. Min Act: -0.0000

Data Index: 926946 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.1055. Min Act: -0.0001

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.3316. Min Act: -0.0000

Data Index: 1096749 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.0096. Min Act: -0.0001

Data Index: 572414 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.1384. Min Act: -0.0000

Data Index: 1098690 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.9440. Min Act: -0.0000

Data Index: 860378 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.7847. Min Act: -0.0000

Data Index: 639532 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.9401. Min Act: -0.0000

Data Index: 1310400 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.0151. Min Act: -0.0001

Data Index: 73123 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.8974. Min Act: -0.0001

Data Index: 323832 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 3.7374. Min Range: -3.7374

Max Act: 3.0215. Min Act: -0.0001

Data Index: 1335054 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.8600. Min Act: -0.0001

Data Index: 413650 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.7343. Min Act: -0.0001

Data Index: 245497 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.5712. Min Act: -0.0001

Data Index: 134438 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.9229. Min Act: -0.0001

Data Index: 857169 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.5093. Min Act: -0.0001

Data Index: 761414 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.4278. Min Act: -0.0000

Data Index: 29126 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 3.7374. Min Range: -3.7374

Max Act: 2.6865. Min Act: -0.0000

Data Index: 59579 (C4 (Web Text))

Max Activating Token Index: 287