Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2930 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2913. Min Act: -0.0001

Data Index: 923765 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2897. Min Act: -0.0001

Data Index: 645752 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2890. Min Act: -0.0001

Data Index: 903650 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2783. Min Act: -0.0001

Data Index: 797969 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2717. Min Act: -0.0001

Data Index: 448981 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2615. Min Act: -0.0001

Data Index: 935639 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2249. Min Act: -0.0001

Data Index: 236499 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2818. Min Act: -0.0001

Data Index: 870223 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2539. Min Act: -0.0001

Data Index: 883122 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1253594 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2627. Min Act: -0.0001

Data Index: 531619 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1071340 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2353. Min Act: -0.0001

Data Index: 536672 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1137443 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2454. Min Act: -0.0001

Data Index: 39048 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1216953 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2374. Min Act: -0.0001

Data Index: 254858 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2257. Min Act: -0.0001

Data Index: 248467 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2171. Min Act: -0.0001

Data Index: 579790 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.2913. Min Range: -0.2913

Max Act: 0.2518. Min Act: -0.0001

Data Index: 475443 (C4 (Web Text))

Max Activating Token Index: 299