Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2812 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1173845 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1035548 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1547043 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0336. Min Act: -0.0002

Data Index: 494544 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1020993 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0311. Min Act: -0.0002

Data Index: 902365 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1191282 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0279. Min Act: -0.0002

Data Index: 432713 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0292. Min Act: -0.0002

Data Index: 662427 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0287. Min Act: -0.0002

Data Index: 367390 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1493788 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1285787 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1057384 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1259301 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1170726 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1588088 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0265. Min Act: -0.0002

Data Index: 214086 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0259. Min Act: -0.0002

Data Index: 176994 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0264. Min Act: -0.0002

Data Index: 587582 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0259. Min Act: -0.0002

Data Index: 620277 (C4 (Web Text))

Max Activating Token Index: 207