Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3198 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.4147. Min Act: -0.0001

Data Index: 529921 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3984. Min Act: -0.0001

Data Index: 938681 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1290194 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3571. Min Act: -0.0001

Data Index: 28156 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3336. Min Act: -0.0000

Data Index: 539889 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3302. Min Act: -0.0001

Data Index: 403848 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3157. Min Act: -0.0001

Data Index: 588683 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3589. Min Act: -0.0000

Data Index: 492676 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1207812 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3348. Min Act: -0.0001

Data Index: 67846 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3349. Min Act: -0.0001

Data Index: 198123 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3245. Min Act: -0.0001

Data Index: 886983 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3322. Min Act: -0.0001

Data Index: 722307 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3188. Min Act: -0.0001

Data Index: 1180719 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3303. Min Act: -0.0001

Data Index: 17970 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3233. Min Act: -0.0001

Data Index: 616136 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.3212. Min Act: -0.0001

Data Index: 1082006 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1297997 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2845. Min Act: -0.0001

Data Index: 1223423 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.4147. Min Range: -0.4147

Max Act: 0.2913. Min Act: -0.0001

Data Index: 460488 (C4 (Web Text))

Max Activating Token Index: 417