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

Dataset: The Pile

Neuron 3627 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1623877 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1414253 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6980. Min Act: -0.0000

Data Index: 89863 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1177072 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1208524 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1317236 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6631. Min Act: -0.0000

Data Index: 316132 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1072675 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1607111 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1825556 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6320. Min Act: -0.0000

Data Index: 881937 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6231. Min Act: -0.0000

Data Index: 397233 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1227854 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5910. Min Act: -0.0000

Data Index: 943602 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1922017 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5453. Min Act: -0.0000

Data Index: 524233 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1584570 (The Pile)

Max Activating Token Index: 134

Text #17

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5929. Min Act: -0.0000

Data Index: 521518 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1115588 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1538423 (The Pile)

Max Activating Token Index: 872