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

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

Neuron 200 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1404. Min Range: -1.1404

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1164068 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1110340 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.7753. Min Act: -0.0000

Data Index: 731795 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6996. Min Act: -0.0000

Data Index: 515202 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1197121 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.7428. Min Act: -0.0000

Data Index: 74652 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6514. Min Act: -0.0000

Data Index: 266572 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1120157 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.7208. Min Act: -0.0000

Data Index: 463934 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6905. Min Act: -0.0000

Data Index: 442079 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.7885. Min Act: -0.0000

Data Index: 353194 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1171515 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6465. Min Act: -0.0000

Data Index: 22074 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1165460 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6443. Min Act: -0.0000

Data Index: 296963 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6444. Min Act: -0.0000

Data Index: 360629 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.5798. Min Act: -0.0000

Data Index: 694050 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.6233. Min Act: -0.0000

Data Index: 467333 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.5961. Min Act: -0.0000

Data Index: 70440 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.1404. Min Range: -1.1404

Max Act: 0.5872. Min Act: -0.0000

Data Index: 356469 (C4 (Web Text))

Max Activating Token Index: 114