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

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

Neuron 684 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0729. Min Range: -1.0729

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1369083 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.8819. Min Act: -0.0000

Data Index: 102807 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.9172. Min Act: -0.0000

Data Index: 921292 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1504832 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1462889 (Python Code)

Max Activating Token Index: 186

Text #5

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1589492 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1631291 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1113417 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1550928 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1505648 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7279. Min Act: -0.0000

Data Index: 807640 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.6790. Min Act: -0.0000

Data Index: 460662 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1475639 (Python Code)

Max Activating Token Index: 452

Text #13

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1373126 (Python Code)

Max Activating Token Index: 383

Text #14

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1558133 (Python Code)

Max Activating Token Index: 568

Text #15

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1381476 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.6836. Min Act: -0.0000

Data Index: 549301 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1503934 (Python Code)

Max Activating Token Index: 690

Text #18

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.6503. Min Act: -0.0000

Data Index: 764625 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.0729. Min Range: -1.0729

Max Act: 0.7111. Min Act: -0.0000

Data Index: 472699 (C4 (Web Text))

Max Activating Token Index: 40