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

Dataset: The Pile

Neuron 794 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1859117 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7229. Min Act: 0.0000

Data Index: 1289276 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1976600 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8537. Min Act: -0.0000

Data Index: 334967 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8426. Min Act: -0.0000

Data Index: 455244 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7567. Min Act: -0.0000

Data Index: 812290 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8182. Min Act: -0.0000

Data Index: 602073 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1065906 (The Pile)

Max Activating Token Index: 744

Text #8

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1994489 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1447024 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7206. Min Act: -0.0000

Data Index: 643372 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1163772 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1617654 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1315205 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7174. Min Act: -0.0000

Data Index: 511613 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7988. Min Act: 0.0000

Data Index: 346228 (The Pile)

Max Activating Token Index: 802

Text #16

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1032094 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1261754 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1149971 (The Pile)

Max Activating Token Index: 740

Text #19

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.9082. Min Act: 0.0000

Data Index: 385186 (The Pile)

Max Activating Token Index: 725