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

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

Neuron 1152 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1389546 (Python Code)

Max Activating Token Index: 299

Text #1

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.6450. Min Act: -0.0000

Data Index: 1649626 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1479931 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1377996 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1654760 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1363942 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1570712 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.4199. Min Act: -0.0000

Data Index: 1527387 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.3838. Min Act: -0.0000

Data Index: 1640692 (Python Code)

Max Activating Token Index: 366

Text #9

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2873. Min Act: -0.0000

Data Index: 1432805 (Python Code)

Max Activating Token Index: 330

Text #10

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1573420 (Python Code)

Max Activating Token Index: 185

Text #11

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1606136 (Python Code)

Max Activating Token Index: 339

Text #12

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2298. Min Act: -0.0000

Data Index: 1580945 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2825. Min Act: -0.0000

Data Index: 1389852 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1428335 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1439359 (Python Code)

Max Activating Token Index: 305

Text #16

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2308. Min Act: -0.0000

Data Index: 1594495 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.4450. Min Act: -0.0000

Data Index: 170733 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1569494 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 1.6450. Min Range: -1.6450

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1400211 (Python Code)

Max Activating Token Index: 343