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

Dataset: The Pile

Neuron 2237 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: 1.6777. Min Range: -1.6777

Max Act: 1.6777. Min Act: -0.0000

Data Index: 1272856 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.6510. Min Act: -0.0000

Data Index: 34314 (The Pile)

Max Activating Token Index: 117

Text #2

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4814. Min Act: -0.0000

Data Index: 894722 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1672087 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4696. Min Act: -0.0000

Data Index: 908168 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.5929. Min Act: -0.0000

Data Index: 1682876 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4840. Min Act: -0.0000

Data Index: 1992317 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1846420 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1972900 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3553. Min Act: -0.0000

Data Index: 644962 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1959322 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1267955 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4113. Min Act: -0.0000

Data Index: 1242886 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3702. Min Act: -0.0000

Data Index: 408311 (The Pile)

Max Activating Token Index: 430

Text #14

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3567. Min Act: -0.0000

Data Index: 314436 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3055. Min Act: -0.0000

Data Index: 389837 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3747. Min Act: -0.0000

Data Index: 89670 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4214. Min Act: -0.0000

Data Index: 821622 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1775849 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2927. Min Act: -0.0000

Data Index: 141271 (The Pile)

Max Activating Token Index: 384