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

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

Neuron 388 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8336. Min Range: -4.8336

Max Act: 4.8336. Min Act: -0.0000

Data Index: 473073 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 4.8336. Min Range: -4.8336

Max Act: 4.7844. Min Act: -0.0000

Data Index: 1334648 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 4.8336. Min Range: -4.8336

Max Act: 4.6154. Min Act: -0.0000

Data Index: 252496 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.9430. Min Act: -0.0000

Data Index: 1484670 (Python Code)

Max Activating Token Index: 316

Text #4

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.5888. Min Act: -0.0000

Data Index: 1078394 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.7473. Min Act: -0.0000

Data Index: 193081 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.5816. Min Act: -0.0000

Data Index: 66764 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.5323. Min Act: -0.0000

Data Index: 687914 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.3443. Min Act: -0.0000

Data Index: 966118 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.1865. Min Act: -0.0000

Data Index: 365568 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.3095. Min Act: -0.0000

Data Index: 1325934 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.3853. Min Act: -0.0000

Data Index: 818066 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.0823. Min Act: -0.0000

Data Index: 830564 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.0599. Min Act: -0.0000

Data Index: 1637901 (Python Code)

Max Activating Token Index: 595

Text #14

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.0300. Min Act: -0.0000

Data Index: 921225 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 4.8336. Min Range: -4.8336

Max Act: 2.6901. Min Act: -0.0000

Data Index: 663901 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 4.8336. Min Range: -4.8336

Max Act: 2.9658. Min Act: -0.0000

Data Index: 522067 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.0952. Min Act: -0.0000

Data Index: 988189 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 4.8336. Min Range: -4.8336

Max Act: 2.9207. Min Act: -0.0000

Data Index: 270803 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 4.8336. Min Range: -4.8336

Max Act: 3.0810. Min Act: -0.0000

Data Index: 455128 (C4 (Web Text))

Max Activating Token Index: 759