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

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

Neuron 3086 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: 0.8412. Min Range: -0.8412

Max Act: 0.8412. Min Act: -0.0002

Data Index: 243887 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7657. Min Act: -0.0002

Data Index: 78570 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7581. Min Act: -0.0002

Data Index: 474647 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7193. Min Act: -0.0002

Data Index: 1215738 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7181. Min Act: -0.0002

Data Index: 1025840 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7137. Min Act: -0.0002

Data Index: 343715 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6779. Min Act: -0.0002

Data Index: 151338 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6932. Min Act: -0.0002

Data Index: 125376 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6835. Min Act: -0.0002

Data Index: 215543 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6783. Min Act: -0.0002

Data Index: 735184 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6687. Min Act: -0.0002

Data Index: 418709 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6548. Min Act: -0.0002

Data Index: 650431 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6675. Min Act: -0.0002

Data Index: 452669 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6447. Min Act: -0.0002

Data Index: 794711 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6628. Min Act: -0.0002

Data Index: 1126601 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6442. Min Act: -0.0002

Data Index: 168587 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6479. Min Act: -0.0002

Data Index: 1231235 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6327. Min Act: -0.0002

Data Index: 745534 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6287. Min Act: -0.0002

Data Index: 630910 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6353. Min Act: -0.0002

Data Index: 335809 (C4 (Web Text))

Max Activating Token Index: 692