Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1488 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.9766. Min Act: -0.0002

Data Index: 1071456 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.8955. Min Act: -0.0002

Data Index: 810075 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7785. Min Act: -0.0002

Data Index: 1329136 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7868. Min Act: -0.0002

Data Index: 246781 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7490. Min Act: -0.0002

Data Index: 928491 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7403. Min Act: -0.0002

Data Index: 1022180 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7434. Min Act: -0.0002

Data Index: 296711 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7861. Min Act: -0.0002

Data Index: 874650 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7439. Min Act: -0.0002

Data Index: 1057727 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7485. Min Act: -0.0002

Data Index: 99683 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7526. Min Act: -0.0002

Data Index: 1251746 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7120. Min Act: -0.0002

Data Index: 79206 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7160. Min Act: -0.0002

Data Index: 635248 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.6898. Min Act: -0.0002

Data Index: 1218767 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7139. Min Act: -0.0002

Data Index: 1346500 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7083. Min Act: -0.0002

Data Index: 1141119 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7118. Min Act: -0.0002

Data Index: 457706 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.6531. Min Act: -0.0002

Data Index: 588968 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.6527. Min Act: -0.0002

Data Index: 264596 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.6699. Min Act: -0.0002

Data Index: 1104023 (C4 (Web Text))

Max Activating Token Index: 551