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

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

Neuron 2269 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2568. Min Range: -2.2568

Max Act: 2.2568. Min Act: -0.0000

Data Index: 48361 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.9370. Min Act: -0.0000

Data Index: 540428 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.8136. Min Act: -0.0000

Data Index: 231931 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.6586. Min Act: -0.0001

Data Index: 347457 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.5892. Min Act: -0.0000

Data Index: 365644 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.4522. Min Act: -0.0000

Data Index: 564960 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.3499. Min Act: -0.0000

Data Index: 396412 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1238905 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1173030 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.1588. Min Act: -0.0001

Data Index: 562813 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1109549 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1251078 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.1002. Min Act: -0.0000

Data Index: 914629 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.1061. Min Act: -0.0000

Data Index: 312398 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.0641. Min Act: -0.0000

Data Index: 478657 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.0433. Min Act: -0.0000

Data Index: 392251 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1408796 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 2.2568. Min Range: -2.2568

Max Act: 1.1162. Min Act: -0.0001

Data Index: 356169 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 2.2568. Min Range: -2.2568

Max Act: 0.9980. Min Act: -0.0000

Data Index: 379842 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 2.2568. Min Range: -2.2568

Max Act: 0.9655. Min Act: -0.0000

Data Index: 985697 (C4 (Web Text))

Max Activating Token Index: 283