Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2610 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.3336. Min Act: -0.0000

Data Index: 892543 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2779. Min Act: -0.0000

Data Index: 964439 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2832. Min Act: -0.0001

Data Index: 1264289 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2817. Min Act: -0.0001

Data Index: 360132 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2676. Min Act: -0.0001

Data Index: 1633616 (Python Code)

Max Activating Token Index: 442

Text #5

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2746. Min Act: -0.0001

Data Index: 847564 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1132984 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2339. Min Act: -0.0001

Data Index: 399099 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2417. Min Act: -0.0001

Data Index: 749797 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1116935 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2182. Min Act: -0.0000

Data Index: 162716 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2138. Min Act: -0.0001

Data Index: 1398068 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1566136 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1633580 (Python Code)

Max Activating Token Index: 708

Text #14

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1418579 (Python Code)

Max Activating Token Index: 555

Text #15

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2045. Min Act: -0.0001

Data Index: 684571 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2031. Min Act: -0.0001

Data Index: 53520 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2020. Min Act: -0.0000

Data Index: 349977 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2093. Min Act: -0.0001

Data Index: 292266 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.2003. Min Act: -0.0001

Data Index: 1339305 (C4 (Web Text))

Max Activating Token Index: 729