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

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

Neuron 3672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6503. Min Act: -0.0001

Data Index: 425896 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6465. Min Act: -0.0001

Data Index: 280827 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6008. Min Act: -0.0001

Data Index: 376606 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5969. Min Act: -0.0001

Data Index: 819499 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5789. Min Act: -0.0001

Data Index: 784769 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5955. Min Act: -0.0001

Data Index: 491693 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5326. Min Act: -0.0001

Data Index: 716560 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5280. Min Act: -0.0001

Data Index: 456618 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5120. Min Act: -0.0001

Data Index: 1284698 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.5087. Min Act: -0.0000

Data Index: 689218 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4993. Min Act: -0.0001

Data Index: 617996 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4791. Min Act: -0.0001

Data Index: 102410 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4935. Min Act: -0.0001

Data Index: 843902 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4440. Min Act: -0.0001

Data Index: 614749 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4832. Min Act: -0.0001

Data Index: 253954 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4347. Min Act: -0.0001

Data Index: 211011 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4230. Min Act: -0.0001

Data Index: 1120068 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4775. Min Act: -0.0001

Data Index: 198944 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4545. Min Act: -0.0001

Data Index: 605449 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.4116. Min Act: -0.0001

Data Index: 726379 (C4 (Web Text))

Max Activating Token Index: 150