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

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

Neuron 1733 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: 1.8467. Min Range: -1.8467

Max Act: 1.8467. Min Act: -0.0002

Data Index: 202672 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.8329. Min Act: -0.0003

Data Index: 1091633 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.7399. Min Act: -0.0002

Data Index: 202712 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.7567. Min Act: -0.0002

Data Index: 726778 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.7077. Min Act: -0.0002

Data Index: 204282 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.7105. Min Act: -0.0002

Data Index: 829589 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6780. Min Act: -0.0002

Data Index: 1097048 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6517. Min Act: -0.0002

Data Index: 430493 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6475. Min Act: -0.0002

Data Index: 562271 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6817. Min Act: -0.0002

Data Index: 403732 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6766. Min Act: -0.0002

Data Index: 1183422 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6812. Min Act: -0.0002

Data Index: 753843 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6387. Min Act: -0.0002

Data Index: 427862 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6452. Min Act: -0.0002

Data Index: 41981 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6680. Min Act: -0.0002

Data Index: 707785 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6383. Min Act: -0.0002

Data Index: 654299 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6284. Min Act: -0.0002

Data Index: 205884 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6383. Min Act: -0.0002

Data Index: 528956 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6369. Min Act: -0.0003

Data Index: 42524 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 1.8467. Min Range: -1.8467

Max Act: 1.6171. Min Act: -0.0002

Data Index: 21872 (C4 (Web Text))

Max Activating Token Index: 128