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

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

Neuron 4571 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4923. Min Act: -0.0001

Data Index: 695287 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.3898. Min Act: -0.0001

Data Index: 958165 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2884. Min Act: -0.0001

Data Index: 416365 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2413. Min Act: -0.0001

Data Index: 857720 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.3172. Min Act: -0.0001

Data Index: 137248 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.3709. Min Act: -0.0001

Data Index: 1310110 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1306. Min Act: -0.0001

Data Index: 202177 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2317. Min Act: -0.0001

Data Index: 713272 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2190. Min Act: -0.0001

Data Index: 854836 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1563. Min Act: -0.0001

Data Index: 40787 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2049. Min Act: -0.0001

Data Index: 1212042 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9777. Min Act: -0.0001

Data Index: 365643 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1918. Min Act: -0.0001

Data Index: 657000 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1810. Min Act: -0.0001

Data Index: 511245 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1694. Min Act: -0.0001

Data Index: 110193 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2657. Min Act: -0.0001

Data Index: 1094310 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2349. Min Act: -0.0001

Data Index: 1244849 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1467. Min Act: -0.0001

Data Index: 637609 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2442. Min Act: -0.0001

Data Index: 767298 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1512. Min Act: -0.0002

Data Index: 199543 (C4 (Web Text))

Max Activating Token Index: 936