Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4837 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1314017 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1257168 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1255296 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4434. Min Act: -0.0000

Data Index: 330584 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1038102 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3528. Min Act: -0.0000

Data Index: 995292 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4199. Min Act: -0.0000

Data Index: 76198 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.4172. Min Act: -0.0000

Data Index: 238537 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3523. Min Act: -0.0000

Data Index: 655448 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3596. Min Act: -0.0000

Data Index: 769376 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3406. Min Act: -0.0000

Data Index: 59505 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3612. Min Act: -0.0000

Data Index: 638978 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1318477 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3285. Min Act: -0.0000

Data Index: 205717 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3386. Min Act: -0.0000

Data Index: 887350 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3371. Min Act: -0.0000

Data Index: 393657 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3323. Min Act: -0.0000

Data Index: 850821 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3128. Min Act: -0.0000

Data Index: 610301 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1329596 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.5268. Min Range: -0.5268

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1156871 (C4 (Web Text))

Max Activating Token Index: 370