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

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

Neuron 1863 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.4625. Min Act: -0.0002

Data Index: 1038624 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.4977. Min Act: -0.0002

Data Index: 97446 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.4447. Min Act: -0.0002

Data Index: 968718 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.3963. Min Act: -0.0002

Data Index: 432468 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.3419. Min Act: -0.0002

Data Index: 122639 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.3352. Min Act: -0.0002

Data Index: 20374 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.3182. Min Act: -0.0002

Data Index: 242090 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.3026. Min Act: -0.0002

Data Index: 854200 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.2360. Min Act: -0.0002

Data Index: 230320 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.2098. Min Act: -0.0002

Data Index: 1315046 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.2127. Min Act: -0.0002

Data Index: 700361 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.2547. Min Act: -0.0002

Data Index: 789724 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.1433. Min Act: -0.0002

Data Index: 1100443 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.1493. Min Act: -0.0002

Data Index: 693547 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.1017. Min Act: -0.0002

Data Index: 412637 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.1146. Min Act: -0.0002

Data Index: 1111196 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.1296. Min Act: -0.0002

Data Index: 167473 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.0614. Min Act: -0.0002

Data Index: 781146 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 1.4977. Min Range: -1.4977

Max Act: 1.0755. Min Act: -0.0002

Data Index: 43953 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 1.4977. Min Range: -1.4977

Max Act: 0.9986. Min Act: -0.0002

Data Index: 1282423 (C4 (Web Text))

Max Activating Token Index: 889