Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 755 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0006

Data Index: 788170 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0404. Min Act: -0.0006

Data Index: 389562 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0388. Min Act: -0.0006

Data Index: 116659 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0397. Min Act: -0.0006

Data Index: 790681 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0395. Min Act: -0.0006

Data Index: 590155 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0385. Min Act: -0.0006

Data Index: 1205542 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0384. Min Act: -0.0006

Data Index: 149981 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1268051 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0378. Min Act: -0.0005

Data Index: 878781 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0380. Min Act: -0.0006

Data Index: 1038602 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0372. Min Act: -0.0006

Data Index: 272819 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0380. Min Act: -0.0006

Data Index: 608385 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0378. Min Act: -0.0006

Data Index: 429425 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0362. Min Act: -0.0005

Data Index: 569190 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0353. Min Act: -0.0006

Data Index: 594299 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0367. Min Act: -0.0006

Data Index: 570908 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0365. Min Act: -0.0006

Data Index: 382732 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0349. Min Act: -0.0006

Data Index: 1158706 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0361. Min Act: -0.0006

Data Index: 1134704 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0352. Min Act: -0.0005

Data Index: 208001 (C4 (Web Text))

Max Activating Token Index: 26