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

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

Neuron 3098 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.9848. Min Act: -0.0001

Data Index: 1293104 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8266. Min Act: -0.0001

Data Index: 553902 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8297. Min Act: -0.0001

Data Index: 1304001 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.9369. Min Act: -0.0001

Data Index: 311216 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1336071 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7764. Min Act: -0.0001

Data Index: 1007673 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8130. Min Act: -0.0001

Data Index: 1152454 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7108. Min Act: -0.0001

Data Index: 420946 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7870. Min Act: -0.0001

Data Index: 506677 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7407. Min Act: -0.0001

Data Index: 655919 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7602. Min Act: -0.0001

Data Index: 9409 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7073. Min Act: -0.0001

Data Index: 668735 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6537. Min Act: -0.0001

Data Index: 954246 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7326. Min Act: -0.0001

Data Index: 909765 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6946. Min Act: -0.0001

Data Index: 1056964 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6771. Min Act: -0.0001

Data Index: 482354 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7349. Min Act: -0.0001

Data Index: 951513 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7097. Min Act: -0.0001

Data Index: 211625 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6823. Min Act: -0.0001

Data Index: 1216651 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6762. Min Act: -0.0001

Data Index: 1306283 (C4 (Web Text))

Max Activating Token Index: 483