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

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

Neuron 3640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0363. Min Range: -5.0363

Max Act: 5.0363. Min Act: -0.0000

Data Index: 6678 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 5.0363. Min Range: -5.0363

Max Act: 4.9245. Min Act: -0.0000

Data Index: 1111053 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 5.0363. Min Range: -5.0363

Max Act: 4.7723. Min Act: -0.0000

Data Index: 382081 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 5.0363. Min Range: -5.0363

Max Act: 4.8189. Min Act: -0.0000

Data Index: 1186967 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 5.0363. Min Range: -5.0363

Max Act: 4.3981. Min Act: -0.0000

Data Index: 1009108 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 5.0363. Min Range: -5.0363

Max Act: 4.9377. Min Act: -0.0000

Data Index: 390132 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 5.0363. Min Range: -5.0363

Max Act: 4.0588. Min Act: -0.0000

Data Index: 382534 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.9119. Min Act: -0.0000

Data Index: 344146 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 5.0363. Min Range: -5.0363

Max Act: 4.1609. Min Act: -0.0000

Data Index: 162584 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 5.0363. Min Range: -5.0363

Max Act: 4.0653. Min Act: -0.0000

Data Index: 430594 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.9122. Min Act: -0.0000

Data Index: 1182010 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.9021. Min Act: -0.0000

Data Index: 151957 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.7349. Min Act: -0.0000

Data Index: 1180552 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.7090. Min Act: -0.0000

Data Index: 417741 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.6486. Min Act: -0.0000

Data Index: 628360 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.4930. Min Act: -0.0000

Data Index: 793179 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.4587. Min Act: -0.0000

Data Index: 921856 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.9472. Min Act: -0.0000

Data Index: 473330 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.5250. Min Act: -0.0000

Data Index: 1092777 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 5.0363. Min Range: -5.0363

Max Act: 3.6607. Min Act: -0.0000

Data Index: 1055287 (C4 (Web Text))

Max Activating Token Index: 897