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

Dataset: The Pile

Neuron 1144 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3673. Min Act: -0.0000

Data Index: 620281 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3435. Min Act: -0.0000

Data Index: 431056 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1400839 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3504. Min Act: -0.0000

Data Index: 278117 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3362. Min Act: -0.0000

Data Index: 327579 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3437. Min Act: -0.0000

Data Index: 334993 (The Pile)

Max Activating Token Index: 966

Text #6

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3212. Min Act: -0.0000

Data Index: 851816 (The Pile)

Max Activating Token Index: 892

Text #7

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1661996 (The Pile)

Max Activating Token Index: 933

Text #8

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1552308 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3096. Min Act: -0.0000

Data Index: 943224 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3051. Min Act: -0.0000

Data Index: 278582 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1576796 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3053. Min Act: -0.0000

Data Index: 979057 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3050. Min Act: -0.0000

Data Index: 671317 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1076905 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1017451 (The Pile)

Max Activating Token Index: 840

Text #16

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3132. Min Act: -0.0000

Data Index: 423396 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3215. Min Act: -0.0000

Data Index: 36971 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3176. Min Act: -0.0000

Data Index: 749406 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1129348 (The Pile)

Max Activating Token Index: 463