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

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

Neuron 6032 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.9554. Min Act: -0.0000

Data Index: 1132953 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 3.9554. Min Range: -3.9554

Max Act: 3.5996. Min Act: -0.0000

Data Index: 1211493 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.7571. Min Act: -0.0000

Data Index: 545528 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.5961. Min Act: -0.0000

Data Index: 500472 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.7060. Min Act: -0.0000

Data Index: 1197022 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.6703. Min Act: -0.0000

Data Index: 1338920 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.6082. Min Act: -0.0000

Data Index: 430317 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.6199. Min Act: -0.0000

Data Index: 591758 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.4425. Min Act: -0.0000

Data Index: 818872 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.4829. Min Act: -0.0000

Data Index: 831167 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.2043. Min Act: -0.0000

Data Index: 205265 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.4068. Min Act: -0.0000

Data Index: 1358734 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.5323. Min Act: -0.0000

Data Index: 204972 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.3662. Min Act: -0.0000

Data Index: 390262 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.3807. Min Act: -0.0000

Data Index: 1190096 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.3695. Min Act: -0.0000

Data Index: 256720 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.0248. Min Act: -0.0000

Data Index: 1236031 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.3802. Min Act: -0.0000

Data Index: 27927 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.2473. Min Act: -0.0000

Data Index: 142843 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 3.9554. Min Range: -3.9554

Max Act: 2.4705. Min Act: -0.0000

Data Index: 597541 (C4 (Web Text))

Max Activating Token Index: 485