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

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

Neuron 2837 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.8172. Min Act: -0.0000

Data Index: 71923 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.0538. Min Act: -0.0000

Data Index: 956031 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.5679. Min Act: -0.0000

Data Index: 1312142 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.4818. Min Act: -0.0000

Data Index: 813463 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.2946. Min Act: -0.0000

Data Index: 1285741 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.2527. Min Act: -0.0000

Data Index: 732010 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.2247. Min Act: -0.0000

Data Index: 879153 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1956. Min Act: -0.0000

Data Index: 84658 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 5.8172. Min Range: -5.8172

Max Act: 4.8631. Min Act: -0.0000

Data Index: 1068743 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 5.8172. Min Range: -5.8172

Max Act: 4.9919. Min Act: -0.0000

Data Index: 1127384 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 5.8172. Min Range: -5.8172

Max Act: 4.9676. Min Act: -0.0000

Data Index: 1322009 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1480. Min Act: -0.0000

Data Index: 631730 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1359. Min Act: -0.0000

Data Index: 1058903 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.3200. Min Act: -0.0000

Data Index: 834608 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1067. Min Act: -0.0000

Data Index: 233728 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.1037. Min Act: -0.0000

Data Index: 61704 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.0457. Min Act: -0.0000

Data Index: 1110206 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 5.8172. Min Range: -5.8172

Max Act: 5.0175. Min Act: -0.0000

Data Index: 782226 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 5.8172. Min Range: -5.8172

Max Act: 4.8488. Min Act: -0.0000

Data Index: 886203 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 5.8172. Min Range: -5.8172

Max Act: 4.8760. Min Act: -0.0000

Data Index: 1654 (C4 (Web Text))

Max Activating Token Index: 424