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

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

Neuron 4946 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.8798. Min Act: -0.0001

Data Index: 395458 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.7505. Min Act: -0.0001

Data Index: 794885 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.7451. Min Act: -0.0001

Data Index: 604292 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.7406. Min Act: -0.0001

Data Index: 53090 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.5913. Min Act: -0.0000

Data Index: 251983 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.6461. Min Act: -0.0001

Data Index: 464338 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.4810. Min Act: -0.0000

Data Index: 233573 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.5970. Min Act: -0.0001

Data Index: 1332732 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.5360. Min Act: -0.0000

Data Index: 310391 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.5592. Min Act: -0.0001

Data Index: 234036 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.5118. Min Act: -0.0000

Data Index: 577787 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.5349. Min Act: -0.0000

Data Index: 827424 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.4518. Min Act: -0.0001

Data Index: 1239800 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.4700. Min Act: -0.0001

Data Index: 935329 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.4710. Min Act: -0.0000

Data Index: 236767 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.4235. Min Act: -0.0001

Data Index: 1291543 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.4163. Min Act: -0.0000

Data Index: 940586 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.3265. Min Act: -0.0001

Data Index: 977464 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.3936. Min Act: -0.0000

Data Index: 332219 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.8798. Min Range: -1.8798

Max Act: 1.3310. Min Act: -0.0001

Data Index: 162879 (C4 (Web Text))

Max Activating Token Index: 7