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

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

Neuron 955 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: 2.8038. Min Range: -2.8038

Max Act: 2.8038. Min Act: -0.0000

Data Index: 1412881 (Python Code)

Max Activating Token Index: 719

Text #1

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.7641. Min Act: -0.0000

Data Index: 1514253 (Python Code)

Max Activating Token Index: 503

Text #2

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.7720. Min Act: -0.0000

Data Index: 20584 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.5933. Min Act: -0.0000

Data Index: 988165 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.6905. Min Act: -0.0000

Data Index: 897969 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.4267. Min Act: -0.0000

Data Index: 702086 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.4321. Min Act: -0.0000

Data Index: 608266 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.4081. Min Act: -0.0000

Data Index: 906464 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.5262. Min Act: -0.0000

Data Index: 164140 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.5191. Min Act: -0.0000

Data Index: 289607 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.5187. Min Act: -0.0000

Data Index: 105312 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.4599. Min Act: -0.0000

Data Index: 1331023 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.4411. Min Act: -0.0000

Data Index: 1372532 (Python Code)

Max Activating Token Index: 998

Text #13

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.4717. Min Act: -0.0000

Data Index: 248325 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.4392. Min Act: -0.0000

Data Index: 1310083 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.5633. Min Act: -0.0000

Data Index: 1484201 (Python Code)

Max Activating Token Index: 468

Text #16

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1033978 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.5312. Min Act: -0.0000

Data Index: 134374 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.3909. Min Act: -0.0000

Data Index: 1208102 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 2.8038. Min Range: -2.8038

Max Act: 2.2488. Min Act: -0.0000

Data Index: 1220741 (C4 (Web Text))

Max Activating Token Index: 898