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

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

Neuron 3234 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.3156. Min Act: 0.0000

Data Index: 317820 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2992. Min Act: -0.0000

Data Index: 505567 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.3171. Min Act: 0.0002

Data Index: 1288039 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.3132. Min Act: -0.0000

Data Index: 330378 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.3055. Min Act: 0.0000

Data Index: 651704 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.3101. Min Act: -0.0000

Data Index: 859336 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2851. Min Act: -0.0000

Data Index: 136098 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2879. Min Act: -0.0000

Data Index: 826973 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2747. Min Act: 0.0000

Data Index: 111 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2835. Min Act: 0.0000

Data Index: 550763 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2615. Min Act: 0.0000

Data Index: 276107 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2812. Min Act: -0.0000

Data Index: 85972 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2693. Min Act: 0.0000

Data Index: 979663 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2654. Min Act: -0.0000

Data Index: 882022 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2660. Min Act: 0.0001

Data Index: 887992 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2622. Min Act: -0.0000

Data Index: 522900 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2613. Min Act: 0.0001

Data Index: 1330753 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2683. Min Act: 0.0000

Data Index: 916005 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2575. Min Act: 0.0000

Data Index: 1287842 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1096007 (C4 (Web Text))

Max Activating Token Index: 535