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

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

Neuron 2598 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: 0.9263. Min Range: -0.9263

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1294765 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1167795 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.8573. Min Act: -0.0000

Data Index: 561592 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.8451. Min Act: -0.0000

Data Index: 651523 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.8248. Min Act: -0.0000

Data Index: 587317 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1301697 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1076977 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7720. Min Act: -0.0000

Data Index: 985837 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.8166. Min Act: -0.0000

Data Index: 387095 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7993. Min Act: -0.0000

Data Index: 618500 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7524. Min Act: -0.0001

Data Index: 752092 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7728. Min Act: -0.0001

Data Index: 1253525 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7472. Min Act: -0.0001

Data Index: 1057078 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7666. Min Act: -0.0000

Data Index: 756208 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7617. Min Act: -0.0001

Data Index: 596409 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7394. Min Act: -0.0000

Data Index: 313347 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7191. Min Act: -0.0000

Data Index: 191670 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1357998 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1347086 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7231. Min Act: -0.0000

Data Index: 29764 (C4 (Web Text))

Max Activating Token Index: 1017