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

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

Neuron 5375 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: 1.9526. Min Range: -1.9526

Max Act: 1.9526. Min Act: -0.0002

Data Index: 1068558 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.8418. Min Act: -0.0002

Data Index: 1342577 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.5817. Min Act: -0.0003

Data Index: 42943 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.5173. Min Act: -0.0002

Data Index: 637351 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.4863. Min Act: -0.0002

Data Index: 57399 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.5010. Min Act: -0.0002

Data Index: 459415 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.4626. Min Act: -0.0002

Data Index: 1088237 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.4513. Min Act: -0.0002

Data Index: 912051 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.4516. Min Act: -0.0002

Data Index: 674799 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.4656. Min Act: -0.0002

Data Index: 1284006 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.4006. Min Act: -0.0002

Data Index: 843274 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.3553. Min Act: -0.0002

Data Index: 1341583 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.3642. Min Act: -0.0002

Data Index: 123035 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.4025. Min Act: -0.0002

Data Index: 1295412 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.3767. Min Act: -0.0002

Data Index: 365632 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.4054. Min Act: -0.0002

Data Index: 276124 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.3616. Min Act: -0.0002

Data Index: 1107219 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.3681. Min Act: -0.0002

Data Index: 562566 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.3287. Min Act: -0.0002

Data Index: 1093001 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.9526. Min Range: -1.9526

Max Act: 1.3293. Min Act: -0.0002

Data Index: 203683 (C4 (Web Text))

Max Activating Token Index: 650