Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 640 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0036. Min Act: -0.0006

Data Index: 151887 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0032. Min Act: -0.0006

Data Index: 1286081 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0030. Min Act: -0.0006

Data Index: 420582 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0029. Min Act: -0.0005

Data Index: 475018 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0030. Min Act: -0.0006

Data Index: 388430 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0029. Min Act: -0.0006

Data Index: 1263297 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0029. Min Act: -0.0006

Data Index: 1093620 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0029. Min Act: -0.0005

Data Index: 518910 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0029. Min Act: -0.0006

Data Index: 1186697 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0029. Min Act: -0.0005

Data Index: 204952 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0006

Data Index: 138637 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0005

Data Index: 917862 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0006

Data Index: 46682 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0006

Data Index: 805647 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0005

Data Index: 798309 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0006

Data Index: 678330 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0028. Min Act: -0.0005

Data Index: 706221 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0027. Min Act: -0.0006

Data Index: 33219 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0027. Min Act: -0.0005

Data Index: 792249 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.0036. Min Range: -0.0036

Max Act: 0.0027. Min Act: -0.0005

Data Index: 1335417 (C4 (Web Text))

Max Activating Token Index: 514