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

Dataset: The Pile

Neuron 3560 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.4401. Min Act: -0.0000

Data Index: 727118 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1214965 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3700. Min Act: -0.0000

Data Index: 154107 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1050155 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.3231. Min Act: -0.0000

Data Index: 955304 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2903. Min Act: -0.0000

Data Index: 174105 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2888. Min Act: -0.0000

Data Index: 155990 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2564. Min Act: -0.0000

Data Index: 444914 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1145763 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1058737 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2476. Min Act: -0.0000

Data Index: 18257 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1149184 (The Pile)

Max Activating Token Index: 809

Text #12

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1338407 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2311. Min Act: -0.0000

Data Index: 877547 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2579. Min Act: -0.0000

Data Index: 683882 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2391. Min Act: -0.0000

Data Index: 211027 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2379. Min Act: -0.0000

Data Index: 667661 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1245934 (The Pile)

Max Activating Token Index: 14

Text #18

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1132844 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2305. Min Act: -0.0000

Data Index: 205884 (The Pile)

Max Activating Token Index: 19