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

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

Neuron 1152 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1203. Min Range: -3.1203

Max Act: 3.1203. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.9013. Min Act: -0.0000

Data Index: 465917 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.9146. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.7910. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.7414. Min Act: -0.0000

Data Index: 307887 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.5873. Min Act: -0.0001

Data Index: 1653826 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.3463. Min Act: -0.0001

Data Index: 1411916 (Python Code)

Max Activating Token Index: 536

Text #7

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.3637. Min Act: -0.0001

Data Index: 1381399 (Python Code)

Max Activating Token Index: 548

Text #8

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.2372. Min Act: -0.0000

Data Index: 152845 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.0317. Min Act: -0.0001

Data Index: 1452574 (Python Code)

Max Activating Token Index: 664

Text #10

Max Range: 3.1203. Min Range: -3.1203

Max Act: 2.0574. Min Act: -0.0001

Data Index: 1407449 (Python Code)

Max Activating Token Index: 335

Text #11

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.9346. Min Act: -0.0001

Data Index: 1474942 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.8078. Min Act: -0.0001

Data Index: 1386217 (Python Code)

Max Activating Token Index: 661

Text #13

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.9747. Min Act: -0.0000

Data Index: 1285083 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.9065. Min Act: -0.0001

Data Index: 1561711 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.8950. Min Act: -0.0001

Data Index: 1566224 (Python Code)

Max Activating Token Index: 325

Text #16

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.6167. Min Act: -0.0001

Data Index: 1439343 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.7420. Min Act: -0.0001

Data Index: 1639245 (Python Code)

Max Activating Token Index: 270

Text #18

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.7716. Min Act: -0.0000

Data Index: 860696 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 3.1203. Min Range: -3.1203

Max Act: 1.8482. Min Act: -0.0000

Data Index: 301260 (C4 (Web Text))

Max Activating Token Index: 422