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

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

Neuron 2179 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.6569. Min Act: -0.0001

Data Index: 1371427 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.4198. Min Act: -0.0000

Data Index: 1653259 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1375808 (Python Code)

Max Activating Token Index: 902

Text #3

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.3377. Min Act: -0.0000

Data Index: 1511211 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1443975 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1464223 (Python Code)

Max Activating Token Index: 200

Text #6

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1472572 (Python Code)

Max Activating Token Index: 1015

Text #7

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1441367 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1469532 (Python Code)

Max Activating Token Index: 103

Text #9

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1454468 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1383329 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1521585 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2369. Min Act: -0.0000

Data Index: 1431969 (Python Code)

Max Activating Token Index: 94

Text #13

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1646996 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1510070 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1480268 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1421221 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1633808 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2971. Min Act: -0.0000

Data Index: 1622244 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 1.6569. Min Range: -1.6569

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1609657 (Python Code)

Max Activating Token Index: 8