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

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

Neuron 3661 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: 2.6167. Min Range: -2.6167

Max Act: 2.6167. Min Act: -0.0000

Data Index: 1622243 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 2.6167. Min Range: -2.6167

Max Act: 2.3508. Min Act: -0.0000

Data Index: 1413082 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 2.6167. Min Range: -2.6167

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1521678 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 2.6167. Min Range: -2.6167

Max Act: 2.1489. Min Act: -0.0000

Data Index: 13237 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 2.6167. Min Range: -2.6167

Max Act: 2.0270. Min Act: -0.0000

Data Index: 1648524 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 2.6167. Min Range: -2.6167

Max Act: 2.1212. Min Act: -0.0000

Data Index: 1419395 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.9749. Min Act: -0.0000

Data Index: 1387700 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 2.6167. Min Range: -2.6167

Max Act: 2.1800. Min Act: -0.0000

Data Index: 1315035 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 2.6167. Min Range: -2.6167

Max Act: 2.0552. Min Act: -0.0000

Data Index: 1655824 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1503693 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 2.6167. Min Range: -2.6167

Max Act: 2.0466. Min Act: -0.0000

Data Index: 1468052 (Python Code)

Max Activating Token Index: 533

Text #11

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.9261. Min Act: -0.0000

Data Index: 1423700 (Python Code)

Max Activating Token Index: 762

Text #12

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.9175. Min Act: -0.0000

Data Index: 1437383 (Python Code)

Max Activating Token Index: 372

Text #13

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.9733. Min Act: -0.0000

Data Index: 1596718 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.9483. Min Act: -0.0000

Data Index: 1248494 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.8849. Min Act: -0.0000

Data Index: 1574995 (Python Code)

Max Activating Token Index: 546

Text #16

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.8708. Min Act: -0.0000

Data Index: 1469649 (Python Code)

Max Activating Token Index: 112

Text #17

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.8665. Min Act: -0.0000

Data Index: 1378486 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.9627. Min Act: -0.0000

Data Index: 1553203 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 2.6167. Min Range: -2.6167

Max Act: 1.7326. Min Act: -0.0000

Data Index: 1414382 (Python Code)

Max Activating Token Index: 151