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

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

Neuron 3757 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3335. Min Range: -2.3335

Max Act: 2.0725. Min Act: -0.0000

Data Index: 1347944 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 2.3335. Min Range: -2.3335

Max Act: 2.3335. Min Act: -0.0000

Data Index: 314056 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.8328. Min Act: -0.0000

Data Index: 728653 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.8953. Min Act: -0.0000

Data Index: 568178 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.6334. Min Act: -0.0000

Data Index: 484414 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.6517. Min Act: -0.0000

Data Index: 1174544 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.5567. Min Act: -0.0000

Data Index: 1416478 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.6552. Min Act: -0.0000

Data Index: 1294085 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.5468. Min Act: -0.0000

Data Index: 1436030 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.4583. Min Act: -0.0000

Data Index: 1562957 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1377883 (Python Code)

Max Activating Token Index: 538

Text #11

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1009559 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.4402. Min Act: -0.0000

Data Index: 1426219 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.3779. Min Act: -0.0000

Data Index: 1537180 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.1800. Min Act: -0.0000

Data Index: 1573600 (Python Code)

Max Activating Token Index: 896

Text #15

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1555963 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1460568 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1359890 (Python Code)

Max Activating Token Index: 582

Text #18

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1438131 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 2.3335. Min Range: -2.3335

Max Act: 1.3528. Min Act: -0.0000

Data Index: 621703 (C4 (Web Text))

Max Activating Token Index: 259