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

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

Neuron 3525 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1593901 (Python Code)

Max Activating Token Index: 215

Text #1

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1418408 (Python Code)

Max Activating Token Index: 127

Text #2

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1499833 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1436484 (Python Code)

Max Activating Token Index: 74

Text #4

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1485085 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1389276 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1474322 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1374420 (Python Code)

Max Activating Token Index: 165

Text #8

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1572688 (Python Code)

Max Activating Token Index: 1004

Text #9

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1367172 (Python Code)

Max Activating Token Index: 51

Text #10

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1620649 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1426397 (Python Code)

Max Activating Token Index: 636

Text #12

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1519605 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1584745 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1364561 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1627018 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1408682 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1396160 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1462147 (Python Code)

Max Activating Token Index: 656

Text #19

Max Range: 0.1178. Min Range: -0.1178

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1406781 (Python Code)

Max Activating Token Index: 274