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

Dataset: The Pile

Neuron 3398 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1605338 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9779. Min Act: -0.0000

Data Index: 851990 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1630461 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9674. Min Act: -0.0000

Data Index: 273224 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.0285. Min Act: -0.0000

Data Index: 78905 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9584. Min Act: 0.0000

Data Index: 1105649 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9162. Min Act: -0.0000

Data Index: 407956 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8785. Min Act: -0.0000

Data Index: 427659 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9103. Min Act: -0.0000

Data Index: 400244 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9015. Min Act: -0.0000

Data Index: 1808817 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9171. Min Act: -0.0000

Data Index: 55307 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9069. Min Act: -0.0000

Data Index: 61466 (The Pile)

Max Activating Token Index: 884

Text #12

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8706. Min Act: -0.0000

Data Index: 734463 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1008771 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8369. Min Act: -0.0000

Data Index: 138758 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1264844 (The Pile)

Max Activating Token Index: 553

Text #16

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1611708 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1898427 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8235. Min Act: -0.0000

Data Index: 624876 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7828. Min Act: -0.0000

Data Index: 764387 (The Pile)

Max Activating Token Index: 666