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

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

Neuron 565 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: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0003

Data Index: 529158 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0420. Min Act: -0.0003

Data Index: 396756 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0400. Min Act: -0.0003

Data Index: 550949 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0400. Min Act: -0.0002

Data Index: 904788 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1337061 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0369. Min Act: -0.0003

Data Index: 377765 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0359. Min Act: -0.0002

Data Index: 518010 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0366. Min Act: -0.0003

Data Index: 789493 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1272937 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0342. Min Act: -0.0003

Data Index: 371346 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0326. Min Act: -0.0003

Data Index: 200774 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0328. Min Act: -0.0003

Data Index: 427009 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1153896 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1199940 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0336. Min Act: -0.0003

Data Index: 912113 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0340. Min Act: -0.0003

Data Index: 512842 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0314. Min Act: -0.0003

Data Index: 907304 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0317. Min Act: -0.0002

Data Index: 621112 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0313. Min Act: -0.0003

Data Index: 347713 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0322. Min Act: -0.0003

Data Index: 912536 (C4 (Web Text))

Max Activating Token Index: 949