Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 570 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.4046. Min Range: -5.4046

Max Act: 5.4046. Min Act: -0.0000

Data Index: 1389740 (Python Code)

Max Activating Token Index: 563

Text #1

Max Range: 5.4046. Min Range: -5.4046

Max Act: 4.4191. Min Act: -0.0000

Data Index: 1365808 (Python Code)

Max Activating Token Index: 572

Text #2

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.9897. Min Act: -0.0000

Data Index: 1555029 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 5.4046. Min Range: -5.4046

Max Act: 4.8250. Min Act: -0.0000

Data Index: 1465712 (Python Code)

Max Activating Token Index: 901

Text #4

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.9652. Min Act: -0.0000

Data Index: 1553749 (Python Code)

Max Activating Token Index: 482

Text #5

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.8298. Min Act: -0.0000

Data Index: 1555068 (Python Code)

Max Activating Token Index: 994

Text #6

Max Range: 5.4046. Min Range: -5.4046

Max Act: 4.0705. Min Act: -0.0000

Data Index: 1585495 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.7280. Min Act: -0.0000

Data Index: 1613268 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.7240. Min Act: -0.0000

Data Index: 1368011 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.7686. Min Act: -0.0000

Data Index: 1624024 (Python Code)

Max Activating Token Index: 375

Text #10

Max Range: 5.4046. Min Range: -5.4046

Max Act: 4.1108. Min Act: -0.0000

Data Index: 1414354 (Python Code)

Max Activating Token Index: 422

Text #11

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.9817. Min Act: -0.0000

Data Index: 1627792 (Python Code)

Max Activating Token Index: 348

Text #12

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.9029. Min Act: -0.0000

Data Index: 1567690 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 5.4046. Min Range: -5.4046

Max Act: 4.1315. Min Act: -0.0000

Data Index: 1390140 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 5.4046. Min Range: -5.4046

Max Act: 4.0383. Min Act: -0.0000

Data Index: 1649851 (Python Code)

Max Activating Token Index: 707

Text #15

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.7252. Min Act: 0.0000

Data Index: 1236495 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.9195. Min Act: -0.0000

Data Index: 1445946 (Python Code)

Max Activating Token Index: 996

Text #17

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.9115. Min Act: -0.0000

Data Index: 1527926 (Python Code)

Max Activating Token Index: 621

Text #18

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.7458. Min Act: -0.0000

Data Index: 1484641 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 5.4046. Min Range: -5.4046

Max Act: 3.8352. Min Act: -0.0000

Data Index: 1494126 (Python Code)

Max Activating Token Index: 21