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

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

Neuron 4068 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.9759. Min Act: -0.0000

Data Index: 1254268 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.8292. Min Act: -0.0000

Data Index: 167918 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.6160. Min Act: -0.0000

Data Index: 619975 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.5931. Min Act: -0.0000

Data Index: 1249675 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.4969. Min Act: -0.0000

Data Index: 1166250 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1119109 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.4062. Min Act: -0.0000

Data Index: 354982 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.4064. Min Act: -0.0000

Data Index: 81244 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.4518. Min Act: -0.0000

Data Index: 361499 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.3185. Min Act: -0.0000

Data Index: 367247 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.2203. Min Act: -0.0000

Data Index: 152623 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1179029 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.2578. Min Act: -0.0000

Data Index: 714769 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.1909. Min Act: -0.0000

Data Index: 269750 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.2520. Min Act: -0.0000

Data Index: 1005833 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.2479. Min Act: -0.0000

Data Index: 385307 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.2332. Min Act: -0.0000

Data Index: 573594 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.3207. Min Act: -0.0000

Data Index: 1001073 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.2773. Min Act: -0.0000

Data Index: 963812 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 1.9759. Min Range: -1.9759

Max Act: 1.1738. Min Act: -0.0000

Data Index: 175639 (C4 (Web Text))

Max Activating Token Index: 966