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

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

Neuron 2522 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: 0.5059. Min Range: -0.5059

Max Act: 0.4996. Min Act: -0.0000

Data Index: 4335 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.5059. Min Act: 0.0001

Data Index: 669816 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4291. Min Act: -0.0000

Data Index: 111119 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4388. Min Act: 0.0000

Data Index: 397799 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1160762 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1337777 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4106. Min Act: -0.0000

Data Index: 573336 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.4022. Min Act: -0.0000

Data Index: 352081 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3861. Min Act: -0.0000

Data Index: 224829 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3802. Min Act: -0.0000

Data Index: 985167 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1003100 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3543. Min Act: -0.0000

Data Index: 880957 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3621. Min Act: 0.0000

Data Index: 354519 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3594. Min Act: -0.0000

Data Index: 546399 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3562. Min Act: -0.0000

Data Index: 303544 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3559. Min Act: -0.0000

Data Index: 178626 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3444. Min Act: -0.0000

Data Index: 993362 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1185920 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3384. Min Act: -0.0000

Data Index: 986438 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.5059. Min Range: -0.5059

Max Act: 0.3403. Min Act: -0.0000

Data Index: 403596 (C4 (Web Text))

Max Activating Token Index: 950