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

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

Neuron 3163 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1346013 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0453. Min Act: -0.0003

Data Index: 325717 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0461. Min Act: -0.0003

Data Index: 763873 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0416. Min Act: -0.0003

Data Index: 918119 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1178314 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1072391 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0394. Min Act: -0.0003

Data Index: 812280 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0356. Min Act: -0.0003

Data Index: 625067 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0395. Min Act: -0.0003

Data Index: 35696 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0405. Min Act: -0.0003

Data Index: 332271 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0388. Min Act: -0.0003

Data Index: 229725 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1155852 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0384. Min Act: -0.0003

Data Index: 667544 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0322. Min Act: -0.0003

Data Index: 80710 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1015804 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1326913 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1204496 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0328. Min Act: -0.0003

Data Index: 969324 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0335. Min Act: -0.0003

Data Index: 456797 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1045570 (C4 (Web Text))

Max Activating Token Index: 668