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

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

Neuron 4362 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0958. Min Range: -2.0958

Max Act: 2.0139. Min Act: -0.0000

Data Index: 507628 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 2.0958. Min Range: -2.0958

Max Act: 2.0129. Min Act: -0.0000

Data Index: 1199060 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 2.0958. Min Range: -2.0958

Max Act: 2.0958. Min Act: -0.0000

Data Index: 893664 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1340390 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.7439. Min Act: -0.0000

Data Index: 85397 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.7952. Min Act: -0.0000

Data Index: 1125217 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.8496. Min Act: -0.0000

Data Index: 63770 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.7463. Min Act: -0.0000

Data Index: 836386 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.7185. Min Act: -0.0000

Data Index: 226446 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.7186. Min Act: -0.0000

Data Index: 1060094 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.7116. Min Act: -0.0000

Data Index: 143425 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.6883. Min Act: -0.0000

Data Index: 1047515 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.7004. Min Act: -0.0000

Data Index: 417703 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.6879. Min Act: -0.0000

Data Index: 1181838 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.6782. Min Act: -0.0000

Data Index: 463354 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.6586. Min Act: -0.0000

Data Index: 636613 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.6450. Min Act: -0.0000

Data Index: 985426 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.7272. Min Act: -0.0000

Data Index: 288540 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.6206. Min Act: -0.0000

Data Index: 1350481 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 2.0958. Min Range: -2.0958

Max Act: 1.5931. Min Act: -0.0000

Data Index: 155870 (C4 (Web Text))

Max Activating Token Index: 956