Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1138 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0447. Min Act: -0.0002

Data Index: 804626 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0428. Min Act: -0.0002

Data Index: 118007 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0445. Min Act: -0.0002

Data Index: 694216 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0433. Min Act: -0.0002

Data Index: 554640 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0419. Min Act: -0.0002

Data Index: 33554 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0404. Min Act: -0.0002

Data Index: 443852 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0369. Min Act: -0.0001

Data Index: 927200 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0395. Min Act: -0.0001

Data Index: 34353 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0393. Min Act: -0.0002

Data Index: 409595 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0375. Min Act: -0.0002

Data Index: 311797 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1084208 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0364. Min Act: -0.0001

Data Index: 265005 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0365. Min Act: -0.0002

Data Index: 387212 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1051180 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0361. Min Act: -0.0001

Data Index: 920386 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1008567 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1305721 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0328. Min Act: -0.0002

Data Index: 888077 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0347. Min Act: -0.0002

Data Index: 61810 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0336. Min Act: -0.0001

Data Index: 144321 (C4 (Web Text))

Max Activating Token Index: 51