Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2514 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.5319. Min Act: -0.0001

Data Index: 202803 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.5147. Min Act: -0.0001

Data Index: 29172 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4732. Min Act: -0.0001

Data Index: 822449 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4877. Min Act: -0.0001

Data Index: 158720 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4837. Min Act: -0.0001

Data Index: 1323396 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.5150. Min Act: -0.0001

Data Index: 1326480 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1281253 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4623. Min Act: -0.0001

Data Index: 772145 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4474. Min Act: -0.0001

Data Index: 1255115 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4646. Min Act: -0.0001

Data Index: 477411 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4358. Min Act: -0.0000

Data Index: 718872 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4500. Min Act: -0.0001

Data Index: 436085 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4489. Min Act: -0.0001

Data Index: 249679 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4314. Min Act: -0.0001

Data Index: 1174657 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4324. Min Act: -0.0001

Data Index: 712159 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4467. Min Act: -0.0000

Data Index: 633508 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1250065 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4253. Min Act: -0.0001

Data Index: 560013 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4409. Min Act: -0.0001

Data Index: 687048 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4237. Min Act: -0.0001

Data Index: 274698 (C4 (Web Text))

Max Activating Token Index: 408