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

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

Neuron 3587 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: 3.4163. Min Range: -3.4163

Max Act: 3.4163. Min Act: -0.0000

Data Index: 85234 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.2718. Min Act: -0.0000

Data Index: 90018 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.8562. Min Act: -0.0000

Data Index: 867812 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.9758. Min Act: -0.0000

Data Index: 1108082 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.6522. Min Act: -0.0000

Data Index: 1336990 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.6259. Min Act: -0.0000

Data Index: 1183634 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5303. Min Act: -0.0000

Data Index: 576343 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5181. Min Act: -0.0000

Data Index: 177075 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5033. Min Act: -0.0000

Data Index: 494348 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5772. Min Act: -0.0000

Data Index: 798801 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.3171. Min Act: -0.0000

Data Index: 1099843 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5407. Min Act: -0.0000

Data Index: 550761 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.3003. Min Act: -0.0000

Data Index: 140790 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.3741. Min Act: -0.0000

Data Index: 1178548 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.3626. Min Act: -0.0000

Data Index: 695282 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2873. Min Act: -0.0000

Data Index: 938336 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.3749. Min Act: -0.0000

Data Index: 241692 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2145. Min Act: -0.0000

Data Index: 810686 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.1545. Min Act: -0.0000

Data Index: 672602 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.0038. Min Act: -0.0000

Data Index: 460006 (C4 (Web Text))

Max Activating Token Index: 719