Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2453 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.9084. Min Act: -0.0001

Data Index: 372642 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.7687. Min Act: -0.0001

Data Index: 613478 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.4327. Min Act: -0.0001

Data Index: 82580 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.6014. Min Act: -0.0001

Data Index: 935469 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.1233. Min Act: -0.0001

Data Index: 656506 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.2873. Min Act: -0.0001

Data Index: 1184185 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.0313. Min Act: -0.0001

Data Index: 224128 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.9413. Min Act: -0.0001

Data Index: 470591 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.0460. Min Act: -0.0001

Data Index: 1240684 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.8932. Min Act: -0.0001

Data Index: 250798 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.0847. Min Act: -0.0001

Data Index: 346264 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 8.9084. Min Range: -8.9084

Max Act: 8.0307. Min Act: -0.0001

Data Index: 384617 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.4734. Min Act: -0.0001

Data Index: 956957 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.4291. Min Act: -0.0001

Data Index: 691507 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.6785. Min Act: -0.0001

Data Index: 275102 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.6149. Min Act: -0.0001

Data Index: 181115 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.5615. Min Act: -0.0001

Data Index: 691363 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.6690. Min Act: -0.0001

Data Index: 1064580 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.2665. Min Act: -0.0001

Data Index: 832009 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 8.9084. Min Range: -8.9084

Max Act: 7.2464. Min Act: -0.0001

Data Index: 846385 (C4 (Web Text))

Max Activating Token Index: 373