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

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

Neuron 2240 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: 2.2240. Min Range: -2.2240

Max Act: 2.2240. Min Act: -0.0002

Data Index: 140790 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 2.2240. Min Range: -2.2240

Max Act: 2.1192. Min Act: -0.0002

Data Index: 1181409 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.8374. Min Act: -0.0002

Data Index: 1192594 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.6824. Min Act: -0.0002

Data Index: 459963 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.6970. Min Act: -0.0002

Data Index: 643948 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.6314. Min Act: -0.0002

Data Index: 1148234 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.5446. Min Act: -0.0002

Data Index: 1114441 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.5174. Min Act: -0.0003

Data Index: 734908 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.5449. Min Act: -0.0002

Data Index: 184291 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.4684. Min Act: -0.0002

Data Index: 246243 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.4988. Min Act: -0.0002

Data Index: 315241 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.4761. Min Act: -0.0002

Data Index: 990431 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.4299. Min Act: -0.0002

Data Index: 670023 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.3813. Min Act: -0.0002

Data Index: 1164332 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.3439. Min Act: -0.0002

Data Index: 417515 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.2766. Min Act: -0.0002

Data Index: 737896 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.2982. Min Act: -0.0003

Data Index: 129062 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.2619. Min Act: -0.0002

Data Index: 1354438 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.2720. Min Act: -0.0002

Data Index: 835841 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 2.2240. Min Range: -2.2240

Max Act: 1.2612. Min Act: -0.0002

Data Index: 541131 (C4 (Web Text))

Max Activating Token Index: 851