Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.8901. Min Act: -0.0000

Data Index: 223964 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.8311. Min Act: -0.0000

Data Index: 374922 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6923. Min Act: -0.0000

Data Index: 1133222 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6524. Min Act: -0.0000

Data Index: 931002 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6106. Min Act: -0.0000

Data Index: 841592 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.5073. Min Act: -0.0000

Data Index: 566794 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.5857. Min Act: -0.0000

Data Index: 658827 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.5667. Min Act: -0.0000

Data Index: 946650 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.5325. Min Act: -0.0000

Data Index: 106665 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.6274. Min Act: -0.0000

Data Index: 55844 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.4367. Min Act: -0.0000

Data Index: 1358525 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1141962 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1255567 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.4474. Min Act: -0.0000

Data Index: 139689 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.4819. Min Act: -0.0000

Data Index: 787539 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.4737. Min Act: -0.0000

Data Index: 560890 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.5413. Min Act: -0.0000

Data Index: 412363 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.4467. Min Act: -0.0000

Data Index: 409001 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.4489. Min Act: -0.0000

Data Index: 365016 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.8901. Min Range: -1.8901

Max Act: 1.3461. Min Act: -0.0000

Data Index: 203974 (C4 (Web Text))

Max Activating Token Index: 93