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

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

Neuron 2828 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6538. Min Act: -0.0001

Data Index: 766638 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6749. Min Act: -0.0001

Data Index: 353803 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6306. Min Act: -0.0001

Data Index: 1114646 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5885. Min Act: -0.0001

Data Index: 1135393 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5418. Min Act: -0.0001

Data Index: 395016 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5430. Min Act: -0.0000

Data Index: 773480 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5400. Min Act: -0.0000

Data Index: 238106 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6004. Min Act: -0.0001

Data Index: 404181 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5202. Min Act: -0.0000

Data Index: 330232 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5362. Min Act: -0.0000

Data Index: 184604 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5328. Min Act: -0.0001

Data Index: 25295 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4883. Min Act: -0.0001

Data Index: 296124 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5204. Min Act: -0.0001

Data Index: 296766 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4658. Min Act: -0.0001

Data Index: 1156605 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4463. Min Act: -0.0000

Data Index: 774121 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4897. Min Act: -0.0001

Data Index: 552354 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1302359 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1037744 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4407. Min Act: -0.0001

Data Index: 1183678 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4649. Min Act: -0.0001

Data Index: 595230 (C4 (Web Text))

Max Activating Token Index: 525