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

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

Neuron 2948 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: 1.1098. Min Range: -1.1098

Max Act: 1.1098. Min Act: -0.0000

Data Index: 342257 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9689. Min Act: -0.0000

Data Index: 98277 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.1098. Min Range: -1.1098

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1264565 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 1.1098. Min Range: -1.1098

Max Act: 1.0468. Min Act: -0.0000

Data Index: 724346 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9143. Min Act: -0.0000

Data Index: 241129 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9810. Min Act: -0.0000

Data Index: 216476 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1150407 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1616046 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8484. Min Act: -0.0000

Data Index: 378072 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1005227 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7840. Min Act: -0.0000

Data Index: 101544 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7894. Min Act: -0.0000

Data Index: 342032 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.8449. Min Act: -0.0000

Data Index: 195925 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7663. Min Act: -0.0000

Data Index: 417302 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7320. Min Act: -0.0000

Data Index: 409015 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1364884 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7125. Min Act: -0.0000

Data Index: 365892 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7650. Min Act: -0.0000

Data Index: 833327 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.7366. Min Act: -0.0000

Data Index: 215374 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 1.1098. Min Range: -1.1098

Max Act: 0.6765. Min Act: -0.0000

Data Index: 74299 (C4 (Web Text))

Max Activating Token Index: 354