Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 375 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0006

Data Index: 488245 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0346. Min Act: -0.0006

Data Index: 512334 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0351. Min Act: -0.0006

Data Index: 579737 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0333. Min Act: -0.0006

Data Index: 622548 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0335. Min Act: -0.0006

Data Index: 251618 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0328. Min Act: -0.0006

Data Index: 466187 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0336. Min Act: -0.0006

Data Index: 48246 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0321. Min Act: -0.0006

Data Index: 856772 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0334. Min Act: -0.0006

Data Index: 990097 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0318. Min Act: -0.0006

Data Index: 481784 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0318. Min Act: -0.0006

Data Index: 594124 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0320. Min Act: -0.0006

Data Index: 724997 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0313. Min Act: -0.0006

Data Index: 433945 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0305. Min Act: -0.0006

Data Index: 389560 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0317. Min Act: -0.0006

Data Index: 745326 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0325. Min Act: -0.0006

Data Index: 613218 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1190910 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0322. Min Act: -0.0006

Data Index: 825995 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0313. Min Act: -0.0006

Data Index: 841660 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0314. Min Act: -0.0006

Data Index: 365283 (C4 (Web Text))

Max Activating Token Index: 234