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

Dataset: The Pile

Neuron 1898 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1436105 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1679956 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4169. Min Act: -0.0000

Data Index: 675375 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3626. Min Act: -0.0000

Data Index: 995205 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1007638 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3457. Min Act: -0.0000

Data Index: 910185 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1247525 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1809424 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1809791 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3148. Min Act: -0.0000

Data Index: 167416 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.2957. Min Act: -0.0000

Data Index: 397838 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3084. Min Act: -0.0000

Data Index: 608473 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3066. Min Act: 0.0000

Data Index: 1421458 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3132. Min Act: -0.0000

Data Index: 765301 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1117182 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3544. Min Act: -0.0000

Data Index: 207200 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3094. Min Act: 0.0000

Data Index: 256400 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3058. Min Act: -0.0000

Data Index: 728361 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3078. Min Act: -0.0000

Data Index: 58726 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.3029. Min Act: 0.0000

Data Index: 567912 (The Pile)

Max Activating Token Index: 639