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

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

Neuron 2088 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6995. Min Range: -6.6995

Max Act: 6.6995. Min Act: -0.0000

Data Index: 920244 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 6.6995. Min Range: -6.6995

Max Act: 5.8569. Min Act: -0.0000

Data Index: 481065 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 6.6995. Min Range: -6.6995

Max Act: 5.8287. Min Act: -0.0000

Data Index: 886203 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 6.6995. Min Range: -6.6995

Max Act: 5.5495. Min Act: -0.0000

Data Index: 441744 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 6.6995. Min Range: -6.6995

Max Act: 5.3248. Min Act: -0.0000

Data Index: 110654 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 6.6995. Min Range: -6.6995

Max Act: 5.0141. Min Act: -0.0000

Data Index: 863936 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 6.6995. Min Range: -6.6995

Max Act: 4.7778. Min Act: -0.0000

Data Index: 593883 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 6.6995. Min Range: -6.6995

Max Act: 5.6536. Min Act: -0.0000

Data Index: 1161352 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 6.6995. Min Range: -6.6995

Max Act: 4.2834. Min Act: -0.0000

Data Index: 490134 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 6.6995. Min Range: -6.6995

Max Act: 4.0308. Min Act: -0.0000

Data Index: 382459 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 6.6995. Min Range: -6.6995

Max Act: 4.5675. Min Act: -0.0000

Data Index: 147521 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 6.6995. Min Range: -6.6995

Max Act: 4.6781. Min Act: -0.0000

Data Index: 404188 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 6.6995. Min Range: -6.6995

Max Act: 3.8855. Min Act: -0.0000

Data Index: 303625 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 6.6995. Min Range: -6.6995

Max Act: 4.1026. Min Act: -0.0000

Data Index: 1270980 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 6.6995. Min Range: -6.6995

Max Act: 3.9641. Min Act: -0.0000

Data Index: 1176979 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 6.6995. Min Range: -6.6995

Max Act: 4.0479. Min Act: -0.0000

Data Index: 10697 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 6.6995. Min Range: -6.6995

Max Act: 3.6833. Min Act: -0.0000

Data Index: 79337 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 6.6995. Min Range: -6.6995

Max Act: 3.3755. Min Act: -0.0000

Data Index: 1337252 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 6.6995. Min Range: -6.6995

Max Act: 3.6926. Min Act: -0.0000

Data Index: 1160809 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 6.6995. Min Range: -6.6995

Max Act: 3.8002. Min Act: -0.0000

Data Index: 1062627 (C4 (Web Text))

Max Activating Token Index: 361