Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1313 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.3021. Min Act: -0.0001

Data Index: 1598194 (Python Code)

Max Activating Token Index: 348

Text #1

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2817. Min Act: -0.0001

Data Index: 1389474 (Python Code)

Max Activating Token Index: 439

Text #2

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1475389 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1392441 (Python Code)

Max Activating Token Index: 563

Text #4

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2468. Min Act: -0.0001

Data Index: 1641022 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2327. Min Act: -0.0001

Data Index: 1403055 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1465165 (Python Code)

Max Activating Token Index: 447

Text #7

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2553. Min Act: -0.0001

Data Index: 1577510 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1436712 (Python Code)

Max Activating Token Index: 812

Text #9

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2554. Min Act: -0.0001

Data Index: 1371785 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1531875 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1627471 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2740. Min Act: -0.0001

Data Index: 1499416 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2489. Min Act: -0.0001

Data Index: 1566471 (Python Code)

Max Activating Token Index: 376

Text #14

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1395580 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2655. Min Act: -0.0001

Data Index: 1616591 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2554. Min Act: -0.0001

Data Index: 1561009 (Python Code)

Max Activating Token Index: 214

Text #17

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1367428 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1596915 (Python Code)

Max Activating Token Index: 922

Text #19

Max Range: 0.3021. Min Range: -0.3021

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1498400 (Python Code)

Max Activating Token Index: 507