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

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

Neuron 2400 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.7936. Min Act: -0.0000

Data Index: 426242 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.2212. Min Act: -0.0000

Data Index: 1045077 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.0589. Min Act: -0.0000

Data Index: 276648 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.1566. Min Act: -0.0000

Data Index: 1078607 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.4601. Min Act: -0.0000

Data Index: 985202 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8825. Min Act: -0.0000

Data Index: 1311124 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.0513. Min Act: -0.0000

Data Index: 674117 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1188357 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.0863. Min Act: -0.0000

Data Index: 924112 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.9310. Min Act: -0.0000

Data Index: 804688 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8962. Min Act: -0.0000

Data Index: 853764 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.6912. Min Act: -0.0000

Data Index: 71180 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.9030. Min Act: -0.0000

Data Index: 865055 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8629. Min Act: -0.0000

Data Index: 1065275 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8597. Min Act: -0.0000

Data Index: 619828 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8012. Min Act: -0.0000

Data Index: 841817 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.6927. Min Act: -0.0000

Data Index: 868494 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8041. Min Act: -0.0000

Data Index: 1184384 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 2.7936. Min Range: -2.7936

Max Act: 2.1374. Min Act: -0.0000

Data Index: 5720 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 2.7936. Min Range: -2.7936

Max Act: 1.8860. Min Act: -0.0000

Data Index: 526731 (C4 (Web Text))

Max Activating Token Index: 118