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

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

Neuron 2760 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.6280. Min Act: -0.0000

Data Index: 888043 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5483. Min Act: -0.0000

Data Index: 724912 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5205. Min Act: -0.0000

Data Index: 93020 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5542. Min Act: -0.0000

Data Index: 339130 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1344974 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5458. Min Act: -0.0000

Data Index: 353432 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1310555 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5149. Min Act: -0.0000

Data Index: 691864 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.5041. Min Act: -0.0000

Data Index: 528344 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1061949 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4795. Min Act: -0.0000

Data Index: 619736 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1045773 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4525. Min Act: -0.0000

Data Index: 177506 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4772. Min Act: -0.0000

Data Index: 139458 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1273783 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4857. Min Act: -0.0000

Data Index: 159801 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4583. Min Act: -0.0000

Data Index: 145836 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1041282 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1270 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.6280. Min Range: -0.6280

Max Act: 0.4094. Min Act: -0.0000

Data Index: 867311 (C4 (Web Text))

Max Activating Token Index: 710