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

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

Neuron 464 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.6125. Min Act: -0.0001

Data Index: 1219883 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.4409. Min Act: -0.0002

Data Index: 1149369 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.5325. Min Act: -0.0001

Data Index: 142298 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.3225. Min Act: -0.0002

Data Index: 413900 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.4706. Min Act: -0.0002

Data Index: 446752 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.4052. Min Act: -0.0002

Data Index: 1296709 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.3172. Min Act: -0.0001

Data Index: 516687 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.3609. Min Act: -0.0002

Data Index: 334161 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.3545. Min Act: -0.0002

Data Index: 182821 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.3506. Min Act: -0.0001

Data Index: 827301 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.2466. Min Act: -0.0002

Data Index: 194852 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.1735. Min Act: -0.0001

Data Index: 1193699 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.0201. Min Act: -0.0001

Data Index: 431964 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.2904. Min Act: -0.0001

Data Index: 200963 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.2610. Min Act: -0.0001

Data Index: 1008398 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.3046. Min Act: -0.0002

Data Index: 855932 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.2520. Min Act: -0.0001

Data Index: 989684 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.2148. Min Act: -0.0001

Data Index: 299502 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.2122. Min Act: -0.0001

Data Index: 818558 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.6125. Min Range: -1.6125

Max Act: 1.1832. Min Act: -0.0001

Data Index: 209379 (C4 (Web Text))

Max Activating Token Index: 383