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

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

Neuron 1667 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0056. Min Act: -0.0003

Data Index: 63406 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0055. Min Act: -0.0003

Data Index: 260745 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1493606 (Python Code)

Max Activating Token Index: 467

Text #3

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1409615 (Python Code)

Max Activating Token Index: 178

Text #4

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1644387 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0040. Min Act: -0.0002

Data Index: 1428715 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1110103 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1613300 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1367031 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1649301 (Python Code)

Max Activating Token Index: 812

Text #10

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1058144 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1522392 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1461112 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1114436 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1623311 (Python Code)

Max Activating Token Index: 861

Text #15

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0036. Min Act: -0.0003

Data Index: 633278 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1507647 (Python Code)

Max Activating Token Index: 421

Text #17

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1541383 (Python Code)

Max Activating Token Index: 842

Text #18

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1526131 (Python Code)

Max Activating Token Index: 561

Text #19

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1459497 (Python Code)

Max Activating Token Index: 724