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

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

Neuron 3815 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1459388 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1440688 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1590541 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1465218 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1651386 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1459671 (Python Code)

Max Activating Token Index: 886

Text #6

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1615138 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1377089 (Python Code)

Max Activating Token Index: 450

Text #8

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1541428 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1513223 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1604279 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1554125 (Python Code)

Max Activating Token Index: 455

Text #12

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1379574 (Python Code)

Max Activating Token Index: 758

Text #13

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1524980 (Python Code)

Max Activating Token Index: 634

Text #14

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1541753 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1543285 (Python Code)

Max Activating Token Index: 666

Text #16

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1578303 (Python Code)

Max Activating Token Index: 890

Text #17

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1483665 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1430861 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1602079 (Python Code)

Max Activating Token Index: 675