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

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

Neuron 120 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: 0.4762. Min Range: -0.4762

Max Act: 0.4762. Min Act: -0.0000

Data Index: 708186 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.4263. Min Act: -0.0001

Data Index: 253547 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3655. Min Act: -0.0001

Data Index: 1003051 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3371. Min Act: -0.0000

Data Index: 164155 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3528. Min Act: -0.0001

Data Index: 350823 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3475. Min Act: -0.0001

Data Index: 448686 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3164. Min Act: -0.0001

Data Index: 483365 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3181. Min Act: -0.0000

Data Index: 406135 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3242. Min Act: -0.0001

Data Index: 586084 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3367. Min Act: -0.0000

Data Index: 160667 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1335434 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3120. Min Act: -0.0001

Data Index: 1183311 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3115. Min Act: -0.0001

Data Index: 677401 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.3113. Min Act: -0.0000

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1149032 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2908. Min Act: -0.0000

Data Index: 460253 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2812. Min Act: -0.0000

Data Index: 794999 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2874. Min Act: -0.0000

Data Index: 711260 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2942. Min Act: -0.0001

Data Index: 634068 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.4762. Min Range: -0.4762

Max Act: 0.2685. Min Act: -0.0000

Data Index: 142163 (C4 (Web Text))

Max Activating Token Index: 742