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

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

Neuron 810 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.3155. Min Act: -0.0001

Data Index: 1172140 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.2602. Min Act: -0.0001

Data Index: 1120660 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.3085. Min Act: -0.0001

Data Index: 59115 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1678. Min Act: -0.0002

Data Index: 444861 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.2381. Min Act: -0.0001

Data Index: 528132 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1324675 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.2073. Min Act: -0.0002

Data Index: 1178779 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1724. Min Act: -0.0001

Data Index: 1041511 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.2135. Min Act: -0.0001

Data Index: 1096214 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1594. Min Act: -0.0001

Data Index: 1017227 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1901. Min Act: -0.0001

Data Index: 28484 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0435. Min Act: -0.0001

Data Index: 320737 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.1234. Min Act: -0.0001

Data Index: 1235488 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0791. Min Act: -0.0001

Data Index: 74444 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.2138. Min Act: -0.0001

Data Index: 1346630 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0376. Min Act: -0.0002

Data Index: 11752 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0527. Min Act: -0.0001

Data Index: 499823 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0503. Min Act: -0.0002

Data Index: 908716 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.3155. Min Range: -1.3155

Max Act: 0.9754. Min Act: -0.0001

Data Index: 681492 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 1.3155. Min Range: -1.3155

Max Act: 1.0553. Min Act: -0.0001

Data Index: 1289985 (C4 (Web Text))

Max Activating Token Index: 223