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

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

Neuron 2847 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1127750 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0433. Min Act: -0.0002

Data Index: 145185 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1202662 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0416. Min Act: -0.0002

Data Index: 246187 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0415. Min Act: -0.0002

Data Index: 105270 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0369. Min Act: -0.0003

Data Index: 556342 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0364. Min Act: -0.0003

Data Index: 535791 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0344. Min Act: -0.0002

Data Index: 893799 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1179000 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1306278 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1044939 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0343. Min Act: -0.0003

Data Index: 691532 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0335. Min Act: -0.0002

Data Index: 579634 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0332. Min Act: -0.0003

Data Index: 242598 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0331. Min Act: -0.0003

Data Index: 282640 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1028430 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0333. Min Act: -0.0003

Data Index: 292858 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0338. Min Act: -0.0003

Data Index: 680759 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1103526 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.0507. Min Range: -0.0507

Max Act: 0.0318. Min Act: -0.0002

Data Index: 610176 (C4 (Web Text))

Max Activating Token Index: 95