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

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

Neuron 550 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.3166. Min Act: -0.0003

Data Index: 229029 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2899. Min Act: -0.0003

Data Index: 1014202 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2907. Min Act: -0.0003

Data Index: 191655 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2900. Min Act: -0.0003

Data Index: 195736 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2772. Min Act: -0.0003

Data Index: 353068 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2797. Min Act: -0.0003

Data Index: 598460 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2709. Min Act: -0.0003

Data Index: 851508 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2800. Min Act: -0.0003

Data Index: 703044 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2666. Min Act: -0.0003

Data Index: 333794 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2665. Min Act: -0.0003

Data Index: 1344708 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2660. Min Act: -0.0003

Data Index: 465517 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2618. Min Act: -0.0002

Data Index: 535678 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2704. Min Act: -0.0003

Data Index: 1024156 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2600. Min Act: -0.0003

Data Index: 1059790 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2509. Min Act: -0.0003

Data Index: 1080045 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2576. Min Act: -0.0002

Data Index: 1086488 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2575. Min Act: -0.0003

Data Index: 572225 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2506. Min Act: -0.0003

Data Index: 242113 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2450. Min Act: -0.0003

Data Index: 733940 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2501. Min Act: -0.0003

Data Index: 313196 (C4 (Web Text))

Max Activating Token Index: 928