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

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

Neuron 291 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1411359 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0876. Min Act: -0.0000

Data Index: 192988 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0870. Min Act: -0.0000

Data Index: 977181 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0728. Min Act: -0.0000

Data Index: 537481 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0716. Min Act: -0.0000

Data Index: 998880 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0725. Min Act: -0.0000

Data Index: 220986 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0628. Min Act: -0.0000

Data Index: 239690 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0633. Min Act: -0.0000

Data Index: 997898 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1133239 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0631. Min Act: -0.0000

Data Index: 722192 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0601. Min Act: -0.0000

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0702. Min Act: -0.0000

Data Index: 862034 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1578638 (Python Code)

Max Activating Token Index: 310

Text #13

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0608. Min Act: -0.0000

Data Index: 24235 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1256024 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0608. Min Act: -0.0000

Data Index: 187022 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1236021 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0593. Min Act: -0.0000

Data Index: 766224 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1042077 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0591. Min Act: -0.0000

Data Index: 119401 (C4 (Web Text))

Max Activating Token Index: 829