Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3958 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3228. Min Range: -3.3228

Max Act: 3.3228. Min Act: -0.0000

Data Index: 1473687 (Python Code)

Max Activating Token Index: 314

Text #1

Max Range: 3.3228. Min Range: -3.3228

Max Act: 3.1073. Min Act: -0.0000

Data Index: 1391490 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.8186. Min Act: -0.0000

Data Index: 1476729 (Python Code)

Max Activating Token Index: 632

Text #3

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.7710. Min Act: -0.0000

Data Index: 1452140 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.8067. Min Act: -0.0000

Data Index: 1419018 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.7446. Min Act: -0.0000

Data Index: 1380051 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.6134. Min Act: -0.0000

Data Index: 1596346 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.7272. Min Act: -0.0000

Data Index: 1622084 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.6376. Min Act: -0.0000

Data Index: 1372577 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.6246. Min Act: -0.0000

Data Index: 1499067 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.6924. Min Act: -0.0000

Data Index: 1477169 (Python Code)

Max Activating Token Index: 384

Text #11

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.4306. Min Act: -0.0000

Data Index: 1487651 (Python Code)

Max Activating Token Index: 510

Text #12

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.5631. Min Act: -0.0000

Data Index: 1651179 (Python Code)

Max Activating Token Index: 382

Text #13

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.5518. Min Act: -0.0000

Data Index: 1626122 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.5240. Min Act: -0.0000

Data Index: 1159098 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.4967. Min Act: -0.0000

Data Index: 1648909 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.1308. Min Act: -0.0000

Data Index: 1616945 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.5921. Min Act: -0.0000

Data Index: 1600076 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.4711. Min Act: -0.0000

Data Index: 1643275 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 3.3228. Min Range: -3.3228

Max Act: 2.6888. Min Act: -0.0000

Data Index: 1443846 (Python Code)

Max Activating Token Index: 830