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

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

Neuron 6100 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: 1.7505. Min Range: -1.7505

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1427856 (Python Code)

Max Activating Token Index: 482

Text #1

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1598554 (Python Code)

Max Activating Token Index: 990

Text #2

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1384553 (Python Code)

Max Activating Token Index: 546

Text #3

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1493904 (Python Code)

Max Activating Token Index: 883

Text #4

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1649463 (Python Code)

Max Activating Token Index: 483

Text #5

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1555378 (Python Code)

Max Activating Token Index: 588

Text #6

Max Range: 1.7505. Min Range: -1.7505

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1404649 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1399986 (Python Code)

Max Activating Token Index: 165

Text #8

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0365. Min Act: -0.0000

Data Index: 1550506 (Python Code)

Max Activating Token Index: 163

Text #9

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1485967 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0498. Min Act: -0.0000

Data Index: 1642408 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1388992 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1448225 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0738. Min Act: -0.0000

Data Index: 943235 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0093. Min Act: -0.0000

Data Index: 838005 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0576. Min Act: -0.0000

Data Index: 1542697 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 1.7505. Min Range: -1.7505

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1646448 (Python Code)

Max Activating Token Index: 773

Text #17

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1619080 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0246. Min Act: -0.0000

Data Index: 1515547 (Python Code)

Max Activating Token Index: 385

Text #19

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1613468 (Python Code)

Max Activating Token Index: 23