Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 728 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0411. Min Range: -1.0411

Max Act: 1.0411. Min Act: -0.0001

Data Index: 319742 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.9091. Min Act: -0.0001

Data Index: 1250511 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.9032. Min Act: -0.0001

Data Index: 782483 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.8912. Min Act: -0.0001

Data Index: 589583 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7872. Min Act: -0.0001

Data Index: 1177087 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.8260. Min Act: -0.0001

Data Index: 990167 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7395. Min Act: -0.0001

Data Index: 754350 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7765. Min Act: -0.0001

Data Index: 1308184 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7471. Min Act: -0.0001

Data Index: 843988 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7095. Min Act: -0.0001

Data Index: 349222 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7934. Min Act: -0.0001

Data Index: 1096641 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.6713. Min Act: -0.0001

Data Index: 278321 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.6887. Min Act: -0.0001

Data Index: 1259155 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7861. Min Act: -0.0001

Data Index: 381245 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7130. Min Act: -0.0001

Data Index: 436925 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7798. Min Act: -0.0001

Data Index: 905271 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7354. Min Act: -0.0001

Data Index: 690462 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7313. Min Act: -0.0001

Data Index: 1040033 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.5818. Min Act: -0.0001

Data Index: 768889 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.0411. Min Range: -1.0411

Max Act: 0.7504. Min Act: -0.0001

Data Index: 943490 (C4 (Web Text))

Max Activating Token Index: 823