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

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

Neuron 2786 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.9017. Min Act: -0.0001

Data Index: 390782 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.9246. Min Act: -0.0001

Data Index: 1004365 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8576. Min Act: -0.0001

Data Index: 218293 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8706. Min Act: -0.0001

Data Index: 1050236 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8003. Min Act: -0.0001

Data Index: 554230 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8252. Min Act: -0.0001

Data Index: 785485 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7951. Min Act: -0.0001

Data Index: 985320 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8311. Min Act: -0.0001

Data Index: 249065 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8476. Min Act: -0.0001

Data Index: 1009853 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8338. Min Act: -0.0001

Data Index: 839017 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7439. Min Act: -0.0001

Data Index: 711111 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7957. Min Act: -0.0001

Data Index: 580612 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.8702. Min Act: -0.0001

Data Index: 764277 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7318. Min Act: -0.0001

Data Index: 25033 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7406. Min Act: -0.0001

Data Index: 1155721 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7322. Min Act: -0.0001

Data Index: 591085 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7282. Min Act: -0.0001

Data Index: 1624720 (Python Code)

Max Activating Token Index: 164

Text #17

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7278. Min Act: -0.0001

Data Index: 574402 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7033. Min Act: -0.0001

Data Index: 596406 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.9246. Min Range: -0.9246

Max Act: 0.7169. Min Act: -0.0001

Data Index: 1146111 (C4 (Web Text))

Max Activating Token Index: 791