Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 39 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.2084. Min Act: -0.0001

Data Index: 707394 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.2072. Min Act: -0.0001

Data Index: 577603 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1780. Min Act: -0.0001

Data Index: 310208 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1839. Min Act: -0.0001

Data Index: 709643 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1935. Min Act: -0.0001

Data Index: 27730 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1710. Min Act: -0.0001

Data Index: 152422 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1061931 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1245297 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1528. Min Act: -0.0001

Data Index: 978982 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1419. Min Act: -0.0001

Data Index: 997232 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1235097 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1411. Min Act: -0.0001

Data Index: 310810 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1340. Min Act: -0.0001

Data Index: 714185 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1378. Min Act: -0.0001

Data Index: 561185 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1388. Min Act: -0.0001

Data Index: 748564 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1372. Min Act: -0.0001

Data Index: 224154 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1313. Min Act: -0.0001

Data Index: 867569 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1309. Min Act: -0.0001

Data Index: 743319 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1326. Min Act: -0.0001

Data Index: 731733 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1308. Min Act: -0.0001

Data Index: 81311 (C4 (Web Text))

Max Activating Token Index: 937