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

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

Neuron 140 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8155. Min Act: -0.0002

Data Index: 1002211 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8790. Min Act: -0.0002

Data Index: 242965 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7983. Min Act: -0.0001

Data Index: 1245954 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7614. Min Act: -0.0002

Data Index: 345430 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7255. Min Act: -0.0002

Data Index: 1242965 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7363. Min Act: -0.0001

Data Index: 603036 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7466. Min Act: -0.0001

Data Index: 527685 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7266. Min Act: -0.0001

Data Index: 44616 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7347. Min Act: -0.0002

Data Index: 749196 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6717. Min Act: -0.0002

Data Index: 637555 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6903. Min Act: -0.0002

Data Index: 1102618 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7095. Min Act: -0.0002

Data Index: 440257 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1114767 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6383. Min Act: -0.0001

Data Index: 1092763 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6346. Min Act: -0.0002

Data Index: 396079 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6681. Min Act: -0.0001

Data Index: 659036 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7048. Min Act: -0.0001

Data Index: 352493 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6785. Min Act: -0.0001

Data Index: 776493 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7246. Min Act: -0.0002

Data Index: 870701 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.6556. Min Act: -0.0001

Data Index: 1146184 (C4 (Web Text))

Max Activating Token Index: 764