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

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

Neuron 5117 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: 1.9435. Min Range: -1.9435

Max Act: 1.6338. Min Act: -0.0000

Data Index: 180055 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.9435. Min Act: -0.0000

Data Index: 1459598 (Python Code)

Max Activating Token Index: 721

Text #2

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.6212. Min Act: -0.0000

Data Index: 1264720 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1606095 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1467467 (Python Code)

Max Activating Token Index: 634

Text #5

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1329652 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.3555. Min Act: -0.0000

Data Index: 1426361 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.3036. Min Act: -0.0000

Data Index: 186086 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1650862 (Python Code)

Max Activating Token Index: 743

Text #9

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1019136 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1509260 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.1665. Min Act: -0.0000

Data Index: 549614 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1519737 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.2473. Min Act: -0.0000

Data Index: 957308 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1482513 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1515259 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1513590 (Python Code)

Max Activating Token Index: 695

Text #17

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1408589 (Python Code)

Max Activating Token Index: 1010

Text #18

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.1678. Min Act: -0.0000

Data Index: 106244 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.9435. Min Range: -1.9435

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1177120 (C4 (Web Text))

Max Activating Token Index: 515