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

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

Neuron 964 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1220174 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1029934 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0437. Min Act: -0.0002

Data Index: 963342 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1289154 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1065162 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0341. Min Act: -0.0002

Data Index: 357216 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0338. Min Act: -0.0002

Data Index: 227526 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0337. Min Act: -0.0002

Data Index: 683012 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0333. Min Act: -0.0002

Data Index: 584523 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0330. Min Act: -0.0002

Data Index: 786601 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1005360 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1171622 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1201719 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0320. Min Act: -0.0002

Data Index: 988113 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0319. Min Act: -0.0002

Data Index: 339609 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1046722 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1221705 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0314. Min Act: -0.0002

Data Index: 873380 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1054304 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1005463 (C4 (Web Text))

Max Activating Token Index: 507