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

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

Neuron 3813 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0638. Min Range: -1.0638

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1294933 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.0638. Min Range: -1.0638

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1020550 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.9443. Min Act: -0.0000

Data Index: 325577 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.9330. Min Act: -0.0000

Data Index: 924721 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1008247 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.9055. Min Act: -0.0000

Data Index: 237596 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8364. Min Act: -0.0000

Data Index: 810682 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8153. Min Act: -0.0000

Data Index: 327548 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1064499 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7884. Min Act: -0.0000

Data Index: 537732 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.8428. Min Act: -0.0000

Data Index: 635541 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7654. Min Act: -0.0000

Data Index: 780711 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1261805 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7866. Min Act: -0.0000

Data Index: 223976 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7431. Min Act: -0.0000

Data Index: 609157 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7276. Min Act: -0.0000

Data Index: 671285 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7235. Min Act: -0.0000

Data Index: 521090 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1276924 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7554. Min Act: -0.0000

Data Index: 728198 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.0638. Min Range: -1.0638

Max Act: 0.7516. Min Act: -0.0000

Data Index: 95661 (C4 (Web Text))

Max Activating Token Index: 749