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

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

Neuron 4057 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: 0.3596. Min Range: -0.3596

Max Act: 0.3596. Min Act: -0.0000

Data Index: 964438 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3478. Min Act: -0.0000

Data Index: 396216 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2784. Min Act: -0.0000

Data Index: 686730 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2843. Min Act: -0.0000

Data Index: 996390 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2661. Min Act: -0.0000

Data Index: 560157 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1114312 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2411. Min Act: -0.0000

Data Index: 367107 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2510. Min Act: -0.0000

Data Index: 20191 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2417. Min Act: -0.0000

Data Index: 692667 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2317. Min Act: -0.0000

Data Index: 963824 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2315. Min Act: -0.0000

Data Index: 293044 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2171. Min Act: -0.0000

Data Index: 228302 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2138. Min Act: -0.0000

Data Index: 413126 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2244. Min Act: -0.0000

Data Index: 679986 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2103. Min Act: -0.0000

Data Index: 176378 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2311. Min Act: -0.0000

Data Index: 516511 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1146771 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2213. Min Act: -0.0000

Data Index: 952729 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1014769 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1270981 (C4 (Web Text))

Max Activating Token Index: 301