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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 692 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3470. Min Range: -1.3470

Max Act: 1.3470. Min Act: -0.0000

Data Index: 471115 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9990. Min Act: -0.0000

Data Index: 67668 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8732. Min Act: -0.0000

Data Index: 116114 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1202426 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8026. Min Act: -0.0000

Data Index: 216348 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.9137. Min Act: -0.0000

Data Index: 307782 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8056. Min Act: -0.0000

Data Index: 732568 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8319. Min Act: -0.0000

Data Index: 354559 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7778. Min Act: -0.0001

Data Index: 764319 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7725. Min Act: -0.0001

Data Index: 407744 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7672. Min Act: -0.0001

Data Index: 955888 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8016. Min Act: -0.0001

Data Index: 707875 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.8068. Min Act: -0.0000

Data Index: 592296 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7477. Min Act: -0.0000

Data Index: 980712 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7750. Min Act: -0.0000

Data Index: 87660 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7394. Min Act: -0.0000

Data Index: 421538 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7640. Min Act: -0.0000

Data Index: 220002 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1026876 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7239. Min Act: -0.0000

Data Index: 689603 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 1.3470. Min Range: -1.3470

Max Act: 0.7173. Min Act: -0.0000

Data Index: 643266 (C4 (Web Text))

Max Activating Token Index: 633