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

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

Neuron 2912 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.9149. Min Act: -0.0003

Data Index: 113407 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.9131. Min Act: -0.0003

Data Index: 982226 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.6053. Min Act: -0.0003

Data Index: 438121 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.5613. Min Act: -0.0003

Data Index: 379576 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.3587. Min Act: -0.0003

Data Index: 230605 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.4038. Min Act: -0.0003

Data Index: 30772 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2947. Min Act: -0.0003

Data Index: 512108 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.3515. Min Act: -0.0003

Data Index: 218969 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.3727. Min Act: -0.0003

Data Index: 172738 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2881. Min Act: -0.0003

Data Index: 897787 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.1954. Min Act: -0.0003

Data Index: 1314193 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2957. Min Act: -0.0003

Data Index: 803656 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2856. Min Act: -0.0004

Data Index: 608563 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2460. Min Act: -0.0003

Data Index: 38235 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2467. Min Act: -0.0003

Data Index: 884276 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2615. Min Act: -0.0003

Data Index: 878792 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2613. Min Act: -0.0003

Data Index: 370902 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2563. Min Act: -0.0003

Data Index: 535698 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.2156. Min Act: -0.0003

Data Index: 793028 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 1.9149. Min Range: -1.9149

Max Act: 1.1788. Min Act: -0.0003

Data Index: 264761 (C4 (Web Text))

Max Activating Token Index: 999