Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6305. Min Range: -2.6305

Max Act: 2.5373. Min Act: -0.0000

Data Index: 760788 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 2.6305. Min Range: -2.6305

Max Act: 2.6305. Min Act: -0.0000

Data Index: 377024 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 2.6305. Min Range: -2.6305

Max Act: 2.1983. Min Act: -0.0000

Data Index: 643901 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.9613. Min Act: -0.0000

Data Index: 790315 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.6305. Min Range: -2.6305

Max Act: 2.0740. Min Act: -0.0000

Data Index: 480815 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.8585. Min Act: -0.0000

Data Index: 556913 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.8587. Min Act: -0.0000

Data Index: 784662 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.8745. Min Act: -0.0000

Data Index: 890773 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 2.6305. Min Range: -2.6305

Max Act: 2.2301. Min Act: -0.0000

Data Index: 179647 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.8656. Min Act: -0.0000

Data Index: 793985 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.7914. Min Act: -0.0000

Data Index: 930632 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.7575. Min Act: -0.0000

Data Index: 28053 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.6706. Min Act: -0.0000

Data Index: 912488 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.6466. Min Act: -0.0000

Data Index: 931454 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.6401. Min Act: -0.0000

Data Index: 386607 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1031180 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.7080. Min Act: -0.0000

Data Index: 161001 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.7365. Min Act: -0.0000

Data Index: 169436 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1182097 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 2.6305. Min Range: -2.6305

Max Act: 1.4347. Min Act: -0.0000

Data Index: 655251 (C4 (Web Text))

Max Activating Token Index: 688