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

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

Neuron 2927 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1181325 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.1462. Min Act: -0.0000

Data Index: 897808 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.0703. Min Act: -0.0001

Data Index: 930529 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.1039. Min Act: -0.0000

Data Index: 922986 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.0763. Min Act: -0.0000

Data Index: 703919 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.0206. Min Act: -0.0000

Data Index: 297263 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.0346. Min Act: -0.0000

Data Index: 119300 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.1462. Min Range: -1.1462

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1061334 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9688. Min Act: -0.0000

Data Index: 21189 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9788. Min Act: -0.0000

Data Index: 716500 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9677. Min Act: -0.0000

Data Index: 1244998 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1039952 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9139. Min Act: -0.0000

Data Index: 931712 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.9171. Min Act: -0.0000

Data Index: 690469 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8595. Min Act: -0.0000

Data Index: 573736 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8847. Min Act: -0.0000

Data Index: 534027 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8211. Min Act: -0.0000

Data Index: 996489 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8943. Min Act: -0.0000

Data Index: 9968 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8310. Min Act: -0.0000

Data Index: 498002 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.1462. Min Range: -1.1462

Max Act: 0.8718. Min Act: -0.0000

Data Index: 974477 (C4 (Web Text))

Max Activating Token Index: 377