Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3458 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.9153. Min Act: -0.0001

Data Index: 813760 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 4.2568. Min Range: -4.2568

Max Act: 4.2568. Min Act: -0.0001

Data Index: 1112690 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.8821. Min Act: -0.0001

Data Index: 906215 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.8543. Min Act: -0.0001

Data Index: 565020 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.9909. Min Act: -0.0001

Data Index: 151534 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.8230. Min Act: -0.0001

Data Index: 901345 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 4.2568. Min Range: -4.2568

Max Act: 4.1443. Min Act: -0.0001

Data Index: 1207068 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.7848. Min Act: -0.0001

Data Index: 7274 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.5136. Min Act: -0.0001

Data Index: 1227662 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.9956. Min Act: -0.0001

Data Index: 221835 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.6821. Min Act: -0.0001

Data Index: 352894 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.8336. Min Act: -0.0001

Data Index: 744077 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.9365. Min Act: -0.0001

Data Index: 322909 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.9655. Min Act: -0.0001

Data Index: 216919 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.5857. Min Act: -0.0001

Data Index: 1102517 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.3913. Min Act: -0.0001

Data Index: 711707 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.8639. Min Act: -0.0001

Data Index: 11335 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.5256. Min Act: -0.0001

Data Index: 16501 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.5156. Min Act: -0.0001

Data Index: 1274343 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 4.2568. Min Range: -4.2568

Max Act: 3.8089. Min Act: -0.0001

Data Index: 592640 (C4 (Web Text))

Max Activating Token Index: 602