Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1900 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.5311. Min Act: -0.0003

Data Index: 1004983 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4644. Min Act: -0.0003

Data Index: 938152 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4557. Min Act: -0.0003

Data Index: 973582 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4511. Min Act: -0.0003

Data Index: 1228663 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4361. Min Act: -0.0003

Data Index: 1194437 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4426. Min Act: -0.0003

Data Index: 934046 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4260. Min Act: -0.0003

Data Index: 1256620 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4171. Min Act: -0.0003

Data Index: 1137265 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4090. Min Act: -0.0003

Data Index: 978944 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3980. Min Act: -0.0003

Data Index: 1357063 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3590. Min Act: -0.0003

Data Index: 392760 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3921. Min Act: -0.0003

Data Index: 610602 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3778. Min Act: -0.0003

Data Index: 392926 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3872. Min Act: -0.0003

Data Index: 566941 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3713. Min Act: -0.0003

Data Index: 646052 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3800. Min Act: -0.0003

Data Index: 19056 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3810. Min Act: -0.0003

Data Index: 341137 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3790. Min Act: -0.0003

Data Index: 770751 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3679. Min Act: -0.0003

Data Index: 894801 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3639. Min Act: -0.0003

Data Index: 762643 (C4 (Web Text))

Max Activating Token Index: 684