Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2467 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0002

Data Index: 436828 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1026454 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1310757 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0377. Min Act: -0.0002

Data Index: 105784 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1268492 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0354. Min Act: -0.0002

Data Index: 999416 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1243953 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1042074 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0339. Min Act: -0.0002

Data Index: 304483 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1346702 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0314. Min Act: -0.0002

Data Index: 84243 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1055173 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1301570 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0307. Min Act: -0.0002

Data Index: 510908 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0309. Min Act: -0.0002

Data Index: 829304 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1129245 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0311. Min Act: -0.0002

Data Index: 446658 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0306. Min Act: -0.0002

Data Index: 134679 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0303. Min Act: -0.0002

Data Index: 698139 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0302. Min Act: -0.0002

Data Index: 876173 (C4 (Web Text))

Max Activating Token Index: 90