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

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

Neuron 1999 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.8058. Min Act: -0.0000

Data Index: 17659 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.6742. Min Act: -0.0000

Data Index: 557444 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5335. Min Act: -0.0000

Data Index: 266945 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5589. Min Act: -0.0000

Data Index: 241955 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5582. Min Act: -0.0000

Data Index: 41670 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5734. Min Act: -0.0000

Data Index: 288898 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5520. Min Act: -0.0000

Data Index: 1305612 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5185. Min Act: -0.0000

Data Index: 862542 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5091. Min Act: -0.0000

Data Index: 155148 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.6394. Min Act: -0.0000

Data Index: 893626 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5085. Min Act: -0.0000

Data Index: 135409 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.3686. Min Act: -0.0000

Data Index: 897996 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.4775. Min Act: -0.0000

Data Index: 239075 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.4599. Min Act: -0.0000

Data Index: 638435 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5779. Min Act: -0.0000

Data Index: 83366 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.3626. Min Act: -0.0000

Data Index: 1054536 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.1120. Min Act: -0.0000

Data Index: 871256 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.2023. Min Act: -0.0000

Data Index: 626594 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.1966. Min Act: -0.0000

Data Index: 292860 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.0868. Min Act: -0.0000

Data Index: 278976 (C4 (Web Text))

Max Activating Token Index: 620