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

Dataset: The Pile

Neuron 2923 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: 0.5383. Min Range: -0.5383

Max Act: 0.5383. Min Act: -0.0000

Data Index: 772661 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4575. Min Act: -0.0000

Data Index: 756689 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1558385 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1662525 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1534955 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3641. Min Act: -0.0000

Data Index: 346875 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3757. Min Act: -0.0000

Data Index: 242136 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1113697 (The Pile)

Max Activating Token Index: 652

Text #8

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3828. Min Act: -0.0000

Data Index: 809951 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1021173 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3676. Min Act: -0.0000

Data Index: 628459 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4286. Min Act: -0.0000

Data Index: 403797 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3208. Min Act: -0.0000

Data Index: 66268 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1337599 (The Pile)

Max Activating Token Index: 855

Text #14

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3152. Min Act: -0.0000

Data Index: 298556 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1793198 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1386943 (The Pile)

Max Activating Token Index: 807

Text #17

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1083797 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.3036. Min Act: -0.0000

Data Index: 929116 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1048031 (The Pile)

Max Activating Token Index: 945