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

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

Neuron 2153 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: 1.4951. Min Range: -1.4951

Max Act: 1.4679. Min Act: -0.0002

Data Index: 1250247 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4951. Min Act: -0.0002

Data Index: 933256 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4634. Min Act: -0.0002

Data Index: 316625 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4029. Min Act: -0.0002

Data Index: 881041 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4229. Min Act: -0.0002

Data Index: 982597 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3457. Min Act: -0.0002

Data Index: 604218 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3676. Min Act: -0.0002

Data Index: 652483 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3614. Min Act: -0.0002

Data Index: 1168895 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3575. Min Act: -0.0002

Data Index: 694727 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3781. Min Act: -0.0002

Data Index: 342551 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4010. Min Act: -0.0003

Data Index: 208106 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3606. Min Act: -0.0002

Data Index: 325524 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3632. Min Act: -0.0002

Data Index: 940975 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3584. Min Act: -0.0002

Data Index: 1047962 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3580. Min Act: -0.0002

Data Index: 1167872 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3386. Min Act: -0.0002

Data Index: 1351485 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3471. Min Act: -0.0002

Data Index: 338242 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3514. Min Act: -0.0002

Data Index: 821858 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3388. Min Act: -0.0002

Data Index: 1235632 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3591. Min Act: -0.0002

Data Index: 525771 (C4 (Web Text))

Max Activating Token Index: 523