Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 160 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0003

Data Index: 177861 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0383. Min Act: -0.0003

Data Index: 325456 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0349. Min Act: -0.0003

Data Index: 542471 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0336. Min Act: -0.0003

Data Index: 642460 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0336. Min Act: -0.0003

Data Index: 826679 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0327. Min Act: -0.0003

Data Index: 780846 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1327907 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1046445 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0315. Min Act: -0.0003

Data Index: 91508 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1358185 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0300. Min Act: -0.0003

Data Index: 7694 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0298. Min Act: -0.0003

Data Index: 638055 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1612944 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1196429 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1282678 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1512216 (Python Code)

Max Activating Token Index: 657

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0293. Min Act: -0.0003

Data Index: 582857 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0290. Min Act: -0.0003

Data Index: 696448 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0288. Min Act: -0.0003

Data Index: 785235 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0293. Min Act: -0.0003

Data Index: 663373 (C4 (Web Text))

Max Activating Token Index: 279