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

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

Neuron 5190 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.5728. Min Act: -0.0000

Data Index: 937480 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.4392. Min Act: -0.0000

Data Index: 655546 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.4464. Min Act: -0.0000

Data Index: 865104 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.0915. Min Act: -0.0000

Data Index: 683997 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.3082. Min Act: -0.0000

Data Index: 680501 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.0933. Min Act: -0.0000

Data Index: 288456 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.9861. Min Act: -0.0000

Data Index: 724526 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.1895. Min Act: -0.0000

Data Index: 930410 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.9454. Min Act: -0.0000

Data Index: 1195731 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.2809. Min Act: -0.0000

Data Index: 494463 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.9417. Min Act: -0.0000

Data Index: 236077 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.1360. Min Act: -0.0000

Data Index: 1181024 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.9954. Min Act: -0.0000

Data Index: 278475 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.0897. Min Act: -0.0000

Data Index: 1018391 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 2.5728. Min Range: -2.5728

Max Act: 2.0749. Min Act: -0.0000

Data Index: 1125511 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.9475. Min Act: -0.0000

Data Index: 351608 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.8500. Min Act: -0.0000

Data Index: 673124 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.9295. Min Act: -0.0000

Data Index: 380012 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.9118. Min Act: -0.0000

Data Index: 800352 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 2.5728. Min Range: -2.5728

Max Act: 1.7984. Min Act: -0.0000

Data Index: 577112 (C4 (Web Text))

Max Activating Token Index: 459