Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4259 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0476. Min Act: -0.0003

Data Index: 139823 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0456. Min Act: -0.0003

Data Index: 410268 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1052385 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0413. Min Act: -0.0003

Data Index: 468166 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0403. Min Act: -0.0003

Data Index: 763031 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0401. Min Act: -0.0003

Data Index: 88885 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0416. Min Act: -0.0003

Data Index: 974169 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0408. Min Act: -0.0003

Data Index: 88427 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0417. Min Act: -0.0003

Data Index: 929219 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1359539 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0404. Min Act: -0.0003

Data Index: 138283 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0393. Min Act: -0.0002

Data Index: 786138 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1040844 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1153025 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0397. Min Act: -0.0003

Data Index: 157048 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0400. Min Act: -0.0003

Data Index: 523580 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0400. Min Act: -0.0003

Data Index: 149710 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0381. Min Act: -0.0003

Data Index: 611494 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0383. Min Act: -0.0003

Data Index: 193636 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0476. Min Range: -0.0476

Max Act: 0.0386. Min Act: -0.0003

Data Index: 188701 (C4 (Web Text))

Max Activating Token Index: 786