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

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

Neuron 3939 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: 0.4938. Min Range: -0.4938

Max Act: 0.4901. Min Act: -0.0000

Data Index: 383797 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4938. Min Act: -0.0000

Data Index: 136480 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.4168. Min Act: -0.0000

Data Index: 300638 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1167907 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1154979 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3578. Min Act: -0.0000

Data Index: 658451 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1199448 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2945. Min Act: -0.0000

Data Index: 731665 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3061. Min Act: -0.0000

Data Index: 30042 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1278363 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1282937 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2762. Min Act: -0.0000

Data Index: 813055 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2847. Min Act: -0.0000

Data Index: 762320 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2632. Min Act: -0.0000

Data Index: 388007 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2761. Min Act: -0.0000

Data Index: 968709 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2812. Min Act: -0.0000

Data Index: 368212 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2586. Min Act: -0.0000

Data Index: 358408 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2654. Min Act: -0.0000

Data Index: 64295 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2547. Min Act: -0.0000

Data Index: 118995 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.4938. Min Range: -0.4938

Max Act: 0.2543. Min Act: -0.0000

Data Index: 520383 (C4 (Web Text))

Max Activating Token Index: 194