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

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

Neuron 3148 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: 1.6332. Min Range: -1.6332

Max Act: 1.6332. Min Act: -0.0000

Data Index: 1027504 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.5410. Min Act: -0.0000

Data Index: 1201797 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.4107. Min Act: -0.0000

Data Index: 143307 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.4846. Min Act: -0.0000

Data Index: 1233594 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1031827 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.3214. Min Act: -0.0000

Data Index: 279609 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1065439 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.3037. Min Act: -0.0000

Data Index: 920310 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1443384 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1407069 (Python Code)

Max Activating Token Index: 102

Text #10

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1547121 (Python Code)

Max Activating Token Index: 90

Text #11

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.3287. Min Act: -0.0000

Data Index: 1652637 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1313268 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.2376. Min Act: -0.0000

Data Index: 818369 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1520008 (Python Code)

Max Activating Token Index: 169

Text #15

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1489189 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1542899 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 1.6332. Min Range: -1.6332

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1642139 (Python Code)

Max Activating Token Index: 284

Text #18

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.1773. Min Act: -0.0000

Data Index: 21728 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.6332. Min Range: -1.6332

Max Act: 1.2801. Min Act: -0.0000

Data Index: 1413664 (Python Code)

Max Activating Token Index: 49