Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1052 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1349. Min Range: -2.1349

Max Act: 2.1349. Min Act: -0.0000

Data Index: 547039 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 2.1349. Min Range: -2.1349

Max Act: 2.1234. Min Act: -0.0000

Data Index: 953213 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 2.1349. Min Range: -2.1349

Max Act: 2.0740. Min Act: -0.0000

Data Index: 1084465 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.9611. Min Act: -0.0000

Data Index: 652391 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.8171. Min Act: -0.0000

Data Index: 495055 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.9193. Min Act: -0.0000

Data Index: 442001 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.7938. Min Act: -0.0000

Data Index: 231233 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.6862. Min Act: -0.0000

Data Index: 1005894 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.7572. Min Act: -0.0000

Data Index: 367661 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.6461. Min Act: -0.0000

Data Index: 949810 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.7332. Min Act: -0.0000

Data Index: 503989 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.7236. Min Act: -0.0000

Data Index: 1135996 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.8153. Min Act: -0.0000

Data Index: 512516 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.7218. Min Act: -0.0000

Data Index: 473787 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.6986. Min Act: -0.0000

Data Index: 727960 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.6465. Min Act: -0.0000

Data Index: 72371 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.6850. Min Act: -0.0000

Data Index: 301925 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.6760. Min Act: -0.0000

Data Index: 553593 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.5760. Min Act: -0.0000

Data Index: 1001827 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 2.1349. Min Range: -2.1349

Max Act: 1.6497. Min Act: -0.0000

Data Index: 1229073 (C4 (Web Text))

Max Activating Token Index: 897