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

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

Neuron 3286 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8866. Min Act: -0.0000

Data Index: 110247 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.7835. Min Act: -0.0000

Data Index: 908430 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.4812. Min Act: -0.0000

Data Index: 889909 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.5368. Min Act: -0.0000

Data Index: 962829 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.9534. Min Act: -0.0000

Data Index: 387722 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.4444. Min Act: -0.0000

Data Index: 784859 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.7043. Min Act: -0.0000

Data Index: 574168 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.5553. Min Act: -0.0000

Data Index: 213110 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8151. Min Act: -0.0000

Data Index: 330666 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.5046. Min Act: -0.0000

Data Index: 1215408 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.5162. Min Act: -0.0000

Data Index: 163927 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.8984. Min Act: -0.0000

Data Index: 168302 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.6781. Min Act: -0.0000

Data Index: 1004095 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.6604. Min Act: -0.0000

Data Index: 863684 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.6562. Min Act: -0.0000

Data Index: 838475 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 3.0986. Min Range: -3.0986

Max Act: 3.0986. Min Act: -0.0000

Data Index: 1334654 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.5005. Min Act: -0.0000

Data Index: 16947 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.4185. Min Act: -0.0000

Data Index: 524256 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.4351. Min Act: -0.0000

Data Index: 186945 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 3.0986. Min Range: -3.0986

Max Act: 2.7063. Min Act: -0.0000

Data Index: 1054247 (C4 (Web Text))

Max Activating Token Index: 472