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

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

Neuron 4034 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1096500 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6701. Min Act: -0.0001

Data Index: 79151 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.7302. Min Act: -0.0001

Data Index: 938572 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.6233. Min Act: -0.0001

Data Index: 561221 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5962. Min Act: -0.0001

Data Index: 1313913 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5454. Min Act: -0.0001

Data Index: 640456 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5107. Min Act: -0.0001

Data Index: 421268 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4983. Min Act: -0.0001

Data Index: 306080 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4675. Min Act: -0.0001

Data Index: 496778 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.5383. Min Act: -0.0001

Data Index: 480410 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4678. Min Act: -0.0001

Data Index: 811667 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4692. Min Act: -0.0001

Data Index: 520432 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4990. Min Act: -0.0001

Data Index: 887745 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4622. Min Act: -0.0001

Data Index: 1016910 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4749. Min Act: -0.0001

Data Index: 1237143 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4601. Min Act: -0.0001

Data Index: 1309465 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4601. Min Act: -0.0001

Data Index: 1124513 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4714. Min Act: -0.0001

Data Index: 1036329 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4747. Min Act: -0.0001

Data Index: 138358 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.7823. Min Range: -0.7823

Max Act: 0.4527. Min Act: -0.0001

Data Index: 1096333 (C4 (Web Text))

Max Activating Token Index: 473