Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2367 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.8953. Min Act: -0.0000

Data Index: 836257 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.5702. Min Act: -0.0000

Data Index: 207489 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.4234. Min Act: -0.0000

Data Index: 486948 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.4134. Min Act: -0.0000

Data Index: 19357 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.2467. Min Act: -0.0000

Data Index: 1121535 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.3243. Min Act: -0.0000

Data Index: 101954 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.2348. Min Act: -0.0000

Data Index: 615641 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1328198 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1461. Min Act: -0.0000

Data Index: 542962 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1615. Min Act: -0.0000

Data Index: 632611 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1449. Min Act: -0.0000

Data Index: 798066 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1171. Min Act: -0.0000

Data Index: 492642 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1030. Min Act: -0.0000

Data Index: 861569 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1613. Min Act: -0.0000

Data Index: 1129651 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1152364 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.0454. Min Act: -0.0000

Data Index: 133551 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.8953. Min Range: -1.8953

Max Act: 0.9786. Min Act: -0.0000

Data Index: 1233502 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 1.8953. Min Range: -1.8953

Max Act: 0.9559. Min Act: -0.0000

Data Index: 775242 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.8953. Min Range: -1.8953

Max Act: 0.9956. Min Act: -0.0000

Data Index: 114358 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 1.8953. Min Range: -1.8953

Max Act: 0.9237. Min Act: -0.0000

Data Index: 593782 (C4 (Web Text))

Max Activating Token Index: 328