Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 457 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.5438. Min Act: -0.0001

Data Index: 460083 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4847. Min Act: -0.0001

Data Index: 37902 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.5185. Min Act: -0.0001

Data Index: 715155 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4499. Min Act: -0.0001

Data Index: 661291 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4547. Min Act: -0.0001

Data Index: 344751 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4415. Min Act: -0.0001

Data Index: 945449 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4098. Min Act: -0.0001

Data Index: 931240 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3935. Min Act: -0.0001

Data Index: 236798 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4227. Min Act: -0.0001

Data Index: 122518 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4548. Min Act: -0.0000

Data Index: 880123 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4071. Min Act: -0.0001

Data Index: 1226631 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4560. Min Act: -0.0001

Data Index: 295716 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4067. Min Act: -0.0000

Data Index: 1332196 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3242. Min Act: -0.0001

Data Index: 933759 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.4053. Min Act: -0.0000

Data Index: 1348829 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3441. Min Act: -0.0000

Data Index: 115277 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3836. Min Act: -0.0000

Data Index: 395907 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3418. Min Act: -0.0001

Data Index: 162507 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3637. Min Act: -0.0001

Data Index: 1067711 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 1.5438. Min Range: -1.5438

Max Act: 1.3559. Min Act: -0.0001

Data Index: 351495 (C4 (Web Text))

Max Activating Token Index: 968