Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2795 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7632. Min Act: -0.0001

Data Index: 940938 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7241. Min Act: -0.0001

Data Index: 1133216 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7500. Min Act: -0.0001

Data Index: 1265499 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7904. Min Act: -0.0001

Data Index: 1355789 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6857. Min Act: -0.0001

Data Index: 760725 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6968. Min Act: -0.0001

Data Index: 584034 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6852. Min Act: -0.0001

Data Index: 296411 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6796. Min Act: -0.0001

Data Index: 143181 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5994. Min Act: -0.0001

Data Index: 288152 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6329. Min Act: -0.0001

Data Index: 148182 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6309. Min Act: -0.0001

Data Index: 366100 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6452. Min Act: -0.0001

Data Index: 1065339 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6490. Min Act: -0.0001

Data Index: 261652 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1176273 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6793. Min Act: -0.0001

Data Index: 753121 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5960. Min Act: -0.0001

Data Index: 315510 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6253. Min Act: -0.0001

Data Index: 1325766 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6119. Min Act: -0.0001

Data Index: 975695 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6823. Min Act: -0.0001

Data Index: 912591 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6894. Min Act: -0.0001

Data Index: 989859 (C4 (Web Text))

Max Activating Token Index: 816