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

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

Neuron 577 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: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0003

Data Index: 296154 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0394. Min Act: -0.0003

Data Index: 683361 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0405. Min Act: -0.0003

Data Index: 652632 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0389. Min Act: -0.0003

Data Index: 107056 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0387. Min Act: -0.0002

Data Index: 977291 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0387. Min Act: -0.0002

Data Index: 214786 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1349180 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0369. Min Act: -0.0003

Data Index: 159776 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1125758 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0352. Min Act: -0.0003

Data Index: 99829 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0367. Min Act: -0.0002

Data Index: 539177 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1209810 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0340. Min Act: -0.0002

Data Index: 321694 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0345. Min Act: -0.0003

Data Index: 244736 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0348. Min Act: -0.0003

Data Index: 667964 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0341. Min Act: -0.0002

Data Index: 564245 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1181782 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0330. Min Act: -0.0003

Data Index: 224509 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1151018 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0341. Min Act: -0.0003

Data Index: 640127 (C4 (Web Text))

Max Activating Token Index: 936