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

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

Neuron 4734 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.4925. Min Act: -0.0002

Data Index: 866886 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.4818. Min Act: -0.0002

Data Index: 249289 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3848. Min Act: -0.0002

Data Index: 175836 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.4187. Min Act: -0.0002

Data Index: 1142476 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3946. Min Act: -0.0002

Data Index: 450818 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3734. Min Act: -0.0002

Data Index: 473872 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3440. Min Act: -0.0002

Data Index: 1089016 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3517. Min Act: -0.0002

Data Index: 980639 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.4162. Min Act: -0.0002

Data Index: 1256583 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3426. Min Act: -0.0002

Data Index: 828940 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3494. Min Act: -0.0002

Data Index: 559778 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3248. Min Act: -0.0002

Data Index: 450289 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3667. Min Act: -0.0002

Data Index: 671449 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2942. Min Act: -0.0002

Data Index: 354987 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3139. Min Act: -0.0002

Data Index: 4764 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3283. Min Act: -0.0002

Data Index: 919337 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3009. Min Act: -0.0002

Data Index: 1307937 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3018. Min Act: -0.0002

Data Index: 1047173 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3112. Min Act: -0.0002

Data Index: 1022347 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2974. Min Act: -0.0002

Data Index: 205068 (C4 (Web Text))

Max Activating Token Index: 32