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

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

Neuron 1713 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.9234. Min Act: -0.0000

Data Index: 727169 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.9181. Min Act: -0.0000

Data Index: 466893 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.8337. Min Act: -0.0000

Data Index: 991725 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.8709. Min Act: -0.0000

Data Index: 571023 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1147326 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6329. Min Act: -0.0000

Data Index: 268239 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6276. Min Act: -0.0000

Data Index: 304413 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6210. Min Act: -0.0000

Data Index: 314184 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.6159. Min Act: -0.0000

Data Index: 882820 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5855. Min Act: -0.0000

Data Index: 524461 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5691. Min Act: -0.0000

Data Index: 798806 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5865. Min Act: -0.0000

Data Index: 904508 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1224023 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5409. Min Act: -0.0000

Data Index: 552156 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5169. Min Act: -0.0000

Data Index: 528351 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5680. Min Act: -0.0000

Data Index: 740920 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5381. Min Act: -0.0000

Data Index: 933028 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5032. Min Act: -0.0000

Data Index: 936857 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1078781 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.9234. Min Range: -0.9234

Max Act: 0.4981. Min Act: -0.0001

Data Index: 1330702 (C4 (Web Text))

Max Activating Token Index: 815