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

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

Neuron 1063 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1130964 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0397. Min Act: -0.0003

Data Index: 1220288 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0385. Min Act: -0.0003

Data Index: 186192 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0370. Min Act: -0.0003

Data Index: 624181 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0367. Min Act: -0.0003

Data Index: 455579 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1273239 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1354154 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0365. Min Act: -0.0003

Data Index: 471886 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0354. Min Act: -0.0003

Data Index: 22536 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0354. Min Act: -0.0003

Data Index: 363163 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0340. Min Act: -0.0004

Data Index: 731728 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0348. Min Act: -0.0003

Data Index: 528762 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0339. Min Act: -0.0003

Data Index: 563027 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0346. Min Act: -0.0003

Data Index: 303985 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1093673 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0338. Min Act: -0.0003

Data Index: 634063 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0339. Min Act: -0.0003

Data Index: 190964 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0341. Min Act: -0.0003

Data Index: 717989 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0336. Min Act: -0.0003

Data Index: 428255 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0400. Min Range: -0.0400

Max Act: 0.0336. Min Act: -0.0003

Data Index: 413148 (C4 (Web Text))

Max Activating Token Index: 782