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

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

Neuron 1428 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: 1.3055. Min Range: -1.3055

Max Act: 1.3055. Min Act: -0.0000

Data Index: 514313 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.7951. Min Act: -0.0000

Data Index: 997777 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.8191. Min Act: -0.0000

Data Index: 322483 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.5785. Min Act: -0.0000

Data Index: 732520 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.5944. Min Act: -0.0000

Data Index: 368827 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.9028. Min Act: -0.0000

Data Index: 572207 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.6890. Min Act: -0.0000

Data Index: 656319 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1181873 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.4820. Min Act: -0.0000

Data Index: 959197 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.5148. Min Act: -0.0000

Data Index: 770299 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.5216. Min Act: -0.0000

Data Index: 608226 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.5139. Min Act: -0.0000

Data Index: 523217 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1403378 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.4230. Min Act: -0.0000

Data Index: 237305 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.4219. Min Act: -0.0000

Data Index: 673913 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.4236. Min Act: -0.0000

Data Index: 493616 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.4917. Min Act: -0.0000

Data Index: 526753 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1359093 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1057139 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 1.3055. Min Range: -1.3055

Max Act: 0.3899. Min Act: -0.0000

Data Index: 966834 (C4 (Web Text))

Max Activating Token Index: 583