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

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

Neuron 440 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: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0006

Data Index: 248641 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0346. Min Act: -0.0006

Data Index: 673427 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1304786 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1059308 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0309. Min Act: -0.0006

Data Index: 490560 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0280. Min Act: -0.0006

Data Index: 247847 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0309. Min Act: -0.0006

Data Index: 27305 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1089799 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1137141 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0299. Min Act: -0.0006

Data Index: 224893 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0307. Min Act: -0.0006

Data Index: 924361 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1104106 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0299. Min Act: -0.0006

Data Index: 605366 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0291. Min Act: -0.0006

Data Index: 523095 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0283. Min Act: -0.0006

Data Index: 25199 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1331606 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0274. Min Act: -0.0006

Data Index: 442662 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0267. Min Act: -0.0006

Data Index: 489339 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0284. Min Act: -0.0006

Data Index: 255571 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0271. Min Act: -0.0006

Data Index: 154057 (C4 (Web Text))

Max Activating Token Index: 755