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

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

Neuron 515 in Layer 0

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: 0.0344. Min Range: -0.0344

Max Act: 0.0337. Min Act: -0.0001

Data Index: 410799 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0001

Data Index: 286966 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0332. Min Act: -0.0001

Data Index: 191636 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0330. Min Act: -0.0001

Data Index: 89126 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0329. Min Act: -0.0001

Data Index: 532106 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0336. Min Act: -0.0001

Data Index: 637492 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0332. Min Act: -0.0001

Data Index: 275430 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0334. Min Act: -0.0001

Data Index: 688860 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0322. Min Act: -0.0001

Data Index: 437820 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0322. Min Act: -0.0001

Data Index: 800039 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0323. Min Act: -0.0001

Data Index: 286448 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1146616 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1151642 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0316. Min Act: -0.0001

Data Index: 691253 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1299041 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0311. Min Act: -0.0001

Data Index: 47793 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0317. Min Act: -0.0001

Data Index: 946077 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0311. Min Act: -0.0001

Data Index: 63686 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0310. Min Act: -0.0001

Data Index: 559586 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0307. Min Act: -0.0001

Data Index: 538943 (C4 (Web Text))

Max Activating Token Index: 2