Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3868 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.5463. Min Act: -0.0001

Data Index: 954625 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.5694. Min Act: -0.0001

Data Index: 1328839 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4560. Min Act: -0.0001

Data Index: 1180099 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4437. Min Act: -0.0001

Data Index: 61698 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3961. Min Act: -0.0001

Data Index: 79029 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3059. Min Act: -0.0001

Data Index: 532416 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3695. Min Act: -0.0001

Data Index: 384660 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.4013. Min Act: -0.0001

Data Index: 1256784 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3529. Min Act: -0.0001

Data Index: 998019 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3461. Min Act: -0.0001

Data Index: 1177707 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2666. Min Act: -0.0001

Data Index: 741830 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3468. Min Act: -0.0001

Data Index: 1024934 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2071. Min Act: -0.0001

Data Index: 383814 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3413. Min Act: -0.0001

Data Index: 923554 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2568. Min Act: -0.0001

Data Index: 1354107 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2590. Min Act: -0.0001

Data Index: 1297597 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.3957. Min Act: -0.0001

Data Index: 520705 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2776. Min Act: -0.0001

Data Index: 256121 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.1873. Min Act: -0.0001

Data Index: 973069 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.5694. Min Range: -1.5694

Max Act: 1.2451. Min Act: -0.0001

Data Index: 208598 (C4 (Web Text))

Max Activating Token Index: 74