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

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

Neuron 338 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.9450. Min Act: -0.0001

Data Index: 1382848 (Python Code)

Max Activating Token Index: 829

Text #1

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.8778. Min Act: -0.0001

Data Index: 1466742 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.8391. Min Act: -0.0001

Data Index: 1537289 (Python Code)

Max Activating Token Index: 993

Text #3

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.6397. Min Act: -0.0001

Data Index: 1449338 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.3003. Min Act: -0.0001

Data Index: 1622259 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.1102. Min Act: -0.0001

Data Index: 1612897 (Python Code)

Max Activating Token Index: 962

Text #6

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.3460. Min Act: -0.0001

Data Index: 1594517 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.0065. Min Act: -0.0001

Data Index: 1364940 (Python Code)

Max Activating Token Index: 798

Text #8

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.0574. Min Act: -0.0001

Data Index: 1635993 (Python Code)

Max Activating Token Index: 450

Text #9

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.0090. Min Act: -0.0001

Data Index: 1480712 (Python Code)

Max Activating Token Index: 321

Text #10

Max Range: 3.9450. Min Range: -3.9450

Max Act: 3.0154. Min Act: -0.0001

Data Index: 1571445 (Python Code)

Max Activating Token Index: 407

Text #11

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.8930. Min Act: -0.0001

Data Index: 1385231 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.7965. Min Act: -0.0001

Data Index: 1448434 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.8014. Min Act: -0.0001

Data Index: 1417990 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.7808. Min Act: -0.0001

Data Index: 1602469 (Python Code)

Max Activating Token Index: 602

Text #15

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.7418. Min Act: -0.0001

Data Index: 1397932 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.7887. Min Act: -0.0001

Data Index: 1383374 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.7380. Min Act: -0.0001

Data Index: 1404157 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.9695. Min Act: -0.0001

Data Index: 1655280 (Python Code)

Max Activating Token Index: 700

Text #19

Max Range: 3.9450. Min Range: -3.9450

Max Act: 2.6317. Min Act: -0.0001

Data Index: 1451292 (Python Code)

Max Activating Token Index: 246