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

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

Neuron 3191 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.7499. Min Act: -0.0001

Data Index: 415748 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6869. Min Act: -0.0001

Data Index: 652362 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6909. Min Act: -0.0001

Data Index: 1221063 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6869. Min Act: -0.0001

Data Index: 45854 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6588. Min Act: -0.0001

Data Index: 141573 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6695. Min Act: -0.0001

Data Index: 316101 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6687. Min Act: -0.0001

Data Index: 632965 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6653. Min Act: -0.0001

Data Index: 1135551 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6555. Min Act: -0.0001

Data Index: 249801 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6489. Min Act: -0.0001

Data Index: 340926 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6308. Min Act: -0.0001

Data Index: 1215075 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6252. Min Act: -0.0001

Data Index: 157988 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6172. Min Act: -0.0001

Data Index: 614822 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6212. Min Act: -0.0001

Data Index: 1026661 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6337. Min Act: -0.0001

Data Index: 1228265 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6313. Min Act: -0.0001

Data Index: 988790 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5778. Min Act: -0.0001

Data Index: 223929 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6240. Min Act: -0.0001

Data Index: 1260279 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5789. Min Act: -0.0001

Data Index: 508565 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5986. Min Act: -0.0001

Data Index: 704724 (C4 (Web Text))

Max Activating Token Index: 181