Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4451 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7007. Min Range: -3.7007

Max Act: 3.7007. Min Act: -0.0000

Data Index: 568109 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 3.7007. Min Range: -3.7007

Max Act: 3.0779. Min Act: -0.0000

Data Index: 664944 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 3.7007. Min Range: -3.7007

Max Act: 3.0467. Min Act: -0.0000

Data Index: 686395 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.7630. Min Act: -0.0000

Data Index: 1257921 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.5858. Min Act: -0.0000

Data Index: 1179856 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.5614. Min Act: -0.0000

Data Index: 386033 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.6168. Min Act: -0.0000

Data Index: 175707 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.7169. Min Act: -0.0000

Data Index: 1051757 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.5359. Min Act: -0.0000

Data Index: 1271203 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.4495. Min Act: -0.0000

Data Index: 985694 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.3168. Min Act: -0.0000

Data Index: 555155 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.3933. Min Act: -0.0000

Data Index: 308603 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.3773. Min Act: -0.0000

Data Index: 1043317 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.4425. Min Act: -0.0000

Data Index: 871452 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.3032. Min Act: -0.0000

Data Index: 1091120 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.3754. Min Act: -0.0000

Data Index: 1331262 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.2556. Min Act: -0.0000

Data Index: 1268305 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.3316. Min Act: -0.0000

Data Index: 322427 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.2041. Min Act: -0.0000

Data Index: 751293 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 3.7007. Min Range: -3.7007

Max Act: 2.1879. Min Act: -0.0000

Data Index: 1183485 (C4 (Web Text))

Max Activating Token Index: 672