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

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

Neuron 686 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1350919 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1207059 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0469. Min Act: -0.0000

Data Index: 290636 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0467. Min Act: -0.0000

Data Index: 299806 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0430. Min Act: -0.0000

Data Index: 728429 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0436. Min Act: -0.0000

Data Index: 439448 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0437. Min Act: -0.0000

Data Index: 146488 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0408. Min Act: -0.0000

Data Index: 659421 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1481929 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1107541 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0419. Min Act: -0.0000

Data Index: 1243312 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0394. Min Act: -0.0000

Data Index: 746310 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0366. Min Act: 0.0000

Data Index: 1179980 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0393. Min Act: -0.0000

Data Index: 967683 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0391. Min Act: -0.0000

Data Index: 427641 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0391. Min Act: -0.0000

Data Index: 380844 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0391. Min Act: 0.0000

Data Index: 1648993 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0403. Min Act: -0.0000

Data Index: 132568 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1101825 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.0489. Min Range: -0.0489

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1210078 (C4 (Web Text))

Max Activating Token Index: 242