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

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

Neuron 2242 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: 0.6156. Min Range: -0.6156

Max Act: 0.6156. Min Act: -0.0000

Data Index: 411893 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4688. Min Act: -0.0000

Data Index: 72119 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4286. Min Act: -0.0000

Data Index: 982449 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4428. Min Act: -0.0000

Data Index: 98721 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4542. Min Act: -0.0000

Data Index: 830216 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4361. Min Act: -0.0000

Data Index: 723763 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4332. Min Act: -0.0000

Data Index: 326027 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4672. Min Act: -0.0000

Data Index: 328186 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4376. Min Act: -0.0000

Data Index: 322125 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1222995 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1289166 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1152661 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4102. Min Act: -0.0000

Data Index: 463695 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4075. Min Act: -0.0000

Data Index: 324956 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4044. Min Act: -0.0000

Data Index: 889169 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.3749. Min Act: -0.0000

Data Index: 853865 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4242. Min Act: -0.0000

Data Index: 919517 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.3933. Min Act: -0.0000

Data Index: 290944 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4052. Min Act: -0.0000

Data Index: 39355 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.3906. Min Act: -0.0000

Data Index: 633092 (C4 (Web Text))

Max Activating Token Index: 115