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

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

Neuron 259 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: 0.7711. Min Range: -0.7711

Max Act: 0.7711. Min Act: -0.0001

Data Index: 648909 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.7566. Min Act: -0.0000

Data Index: 127007 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6890. Min Act: -0.0001

Data Index: 1301234 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.7091. Min Act: -0.0001

Data Index: 482093 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6460. Min Act: -0.0001

Data Index: 529283 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1186000 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6405. Min Act: -0.0000

Data Index: 797199 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6681. Min Act: -0.0000

Data Index: 981112 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.5550. Min Act: -0.0000

Data Index: 719022 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6660. Min Act: -0.0001

Data Index: 536773 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1020327 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6392. Min Act: -0.0001

Data Index: 352325 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6337. Min Act: -0.0001

Data Index: 1307311 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6382. Min Act: -0.0001

Data Index: 89515 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6291. Min Act: -0.0000

Data Index: 805384 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6488. Min Act: -0.0001

Data Index: 19640 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1314203 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6225. Min Act: -0.0001

Data Index: 388936 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6055. Min Act: -0.0001

Data Index: 817799 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.7711. Min Range: -0.7711

Max Act: 0.6024. Min Act: -0.0001

Data Index: 1197211 (C4 (Web Text))

Max Activating Token Index: 361