Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4637 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.3662. Min Act: -0.0000

Data Index: 1221371 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.2429. Min Act: -0.0000

Data Index: 732518 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1343451 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.1727. Min Act: -0.0000

Data Index: 674264 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.0963. Min Act: -0.0000

Data Index: 903603 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.1660. Min Act: -0.0000

Data Index: 805300 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.1053. Min Act: -0.0000

Data Index: 975870 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.1366. Min Act: -0.0000

Data Index: 245126 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1052590 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1047594 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1200813 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.9846. Min Act: -0.0000

Data Index: 9318 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.0064. Min Act: -0.0000

Data Index: 790815 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.9593. Min Act: -0.0000

Data Index: 540750 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.3662. Min Range: -1.3662

Max Act: 1.0044. Min Act: -0.0000

Data Index: 352963 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.9370. Min Act: -0.0000

Data Index: 20163 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.9335. Min Act: -0.0000

Data Index: 736314 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.8380. Min Act: -0.0000

Data Index: 950129 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.8442. Min Act: -0.0000

Data Index: 109355 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 1.3662. Min Range: -1.3662

Max Act: 0.8570. Min Act: -0.0000

Data Index: 791230 (C4 (Web Text))

Max Activating Token Index: 339