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

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

Neuron 5839 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: 5.0730. Min Range: -5.0730

Max Act: 4.9459. Min Act: -0.0000

Data Index: 762114 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 5.0730. Min Range: -5.0730

Max Act: 5.0730. Min Act: -0.0000

Data Index: 545000 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 5.0730. Min Range: -5.0730

Max Act: 4.7970. Min Act: -0.0000

Data Index: 1105806 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 5.0730. Min Range: -5.0730

Max Act: 4.2409. Min Act: -0.0000

Data Index: 1072495 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 5.0730. Min Range: -5.0730

Max Act: 4.2324. Min Act: -0.0000

Data Index: 1164137 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 5.0730. Min Range: -5.0730

Max Act: 4.1020. Min Act: -0.0000

Data Index: 994369 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.9635. Min Act: -0.0000

Data Index: 339170 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.7296. Min Act: -0.0000

Data Index: 1265105 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.7223. Min Act: 0.0000

Data Index: 642088 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.7600. Min Act: -0.0000

Data Index: 954416 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.7158. Min Act: -0.0000

Data Index: 1202023 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.6431. Min Act: -0.0000

Data Index: 873079 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.5444. Min Act: -0.0000

Data Index: 333555 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.4728. Min Act: -0.0000

Data Index: 376872 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.4605. Min Act: 0.0000

Data Index: 339839 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.5763. Min Act: -0.0000

Data Index: 70641 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.2352. Min Act: -0.0000

Data Index: 979264 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.4113. Min Act: -0.0000

Data Index: 798547 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.3589. Min Act: -0.0000

Data Index: 295621 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 5.0730. Min Range: -5.0730

Max Act: 3.3906. Min Act: -0.0000

Data Index: 1040645 (C4 (Web Text))

Max Activating Token Index: 522