Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 702 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0412. Min Act: -0.0002

Data Index: 263919 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0454. Min Act: -0.0002

Data Index: 460656 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0290. Min Act: -0.0003

Data Index: 125958 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1153952 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0287. Min Act: -0.0002

Data Index: 631251 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0310. Min Act: -0.0003

Data Index: 290931 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0306. Min Act: -0.0003

Data Index: 526983 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1029724 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0261. Min Act: -0.0003

Data Index: 850382 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1163438 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0312. Min Act: -0.0003

Data Index: 974784 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1204325 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0293. Min Act: -0.0003

Data Index: 394749 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0330. Min Act: -0.0003

Data Index: 159054 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0318. Min Act: -0.0003

Data Index: 893375 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0324. Min Act: -0.0002

Data Index: 882810 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0265. Min Act: -0.0003

Data Index: 56936 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0299. Min Act: -0.0003

Data Index: 964454 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0296. Min Act: -0.0003

Data Index: 549206 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1605274 (Python Code)

Max Activating Token Index: 714