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

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

Neuron 551 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4297. Min Range: -2.4297

Max Act: 2.4297. Min Act: -0.0000

Data Index: 340899 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 2.4297. Min Range: -2.4297

Max Act: 2.0794. Min Act: -0.0000

Data Index: 715892 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1038455 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.8534. Min Act: -0.0000

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.9378. Min Act: -0.0000

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.9467. Min Act: -0.0000

Data Index: 1257550 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.7501. Min Act: -0.0000

Data Index: 1027078 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.6891. Min Act: -0.0000

Data Index: 899435 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.6841. Min Act: -0.0000

Data Index: 781375 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.6692. Min Act: -0.0000

Data Index: 964072 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.7042. Min Act: -0.0000

Data Index: 17254 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.7081. Min Act: 0.0000

Data Index: 829371 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.6166. Min Act: -0.0000

Data Index: 105040 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.5758. Min Act: -0.0000

Data Index: 144540 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.4741. Min Act: -0.0000

Data Index: 1329567 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.5527. Min Act: -0.0000

Data Index: 321854 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.5361. Min Act: -0.0000

Data Index: 1154113 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.5945. Min Act: -0.0000

Data Index: 86965 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.5123. Min Act: -0.0000

Data Index: 437540 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 2.4297. Min Range: -2.4297

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1145707 (C4 (Web Text))

Max Activating Token Index: 70