Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1540 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1288427 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4885. Min Act: -0.0001

Data Index: 299136 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1093999 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4997. Min Act: -0.0001

Data Index: 658121 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4419. Min Act: -0.0000

Data Index: 698217 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1220196 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4342. Min Act: -0.0001

Data Index: 231211 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1069059 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4456. Min Act: -0.0000

Data Index: 708666 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.4112. Min Act: -0.0000

Data Index: 490398 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3971. Min Act: -0.0000

Data Index: 296350 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3814. Min Act: -0.0000

Data Index: 389970 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3836. Min Act: -0.0001

Data Index: 811721 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3966. Min Act: -0.0000

Data Index: 222672 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3788. Min Act: -0.0000

Data Index: 799822 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1200954 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3854. Min Act: -0.0000

Data Index: 959657 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1165225 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3710. Min Act: -0.0000

Data Index: 461954 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.5282. Min Range: -0.5282

Max Act: 0.3659. Min Act: -0.0001

Data Index: 489536 (C4 (Web Text))

Max Activating Token Index: 888