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

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

Neuron 61 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: 0.1100. Min Range: -0.1100

Max Act: 0.1100. Min Act: -0.0002

Data Index: 549715 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0994. Min Act: -0.0002

Data Index: 482235 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0978. Min Act: -0.0002

Data Index: 838813 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0922. Min Act: -0.0002

Data Index: 596759 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0892. Min Act: -0.0002

Data Index: 439247 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0878. Min Act: -0.0002

Data Index: 46103 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1292039 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0900. Min Act: -0.0002

Data Index: 685414 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0885. Min Act: -0.0002

Data Index: 925677 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0887. Min Act: -0.0002

Data Index: 589140 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0841. Min Act: -0.0002

Data Index: 629804 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1210325 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0818. Min Act: -0.0002

Data Index: 787198 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0793. Min Act: -0.0002

Data Index: 200263 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0809. Min Act: -0.0002

Data Index: 975473 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1055930 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0791. Min Act: -0.0002

Data Index: 449289 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0773. Min Act: -0.0002

Data Index: 787673 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0781. Min Act: -0.0002

Data Index: 630565 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0790. Min Act: -0.0002

Data Index: 266867 (C4 (Web Text))

Max Activating Token Index: 550