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

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

Neuron 2036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.4170. Min Act: -0.0000

Data Index: 318488 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3165. Min Act: -0.0001

Data Index: 159240 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3374. Min Act: -0.0001

Data Index: 449627 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3213. Min Act: -0.0001

Data Index: 505375 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1358770 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3065. Min Act: -0.0000

Data Index: 941562 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3113. Min Act: -0.0001

Data Index: 1336116 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3071. Min Act: -0.0000

Data Index: 733928 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2870. Min Act: -0.0001

Data Index: 1081415 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3049. Min Act: -0.0000

Data Index: 877113 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3030. Min Act: -0.0001

Data Index: 753493 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3032. Min Act: -0.0000

Data Index: 238570 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3102. Min Act: -0.0000

Data Index: 234797 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3003. Min Act: -0.0000

Data Index: 406152 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2932. Min Act: -0.0000

Data Index: 46034 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2896. Min Act: -0.0001

Data Index: 53863 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2896. Min Act: -0.0001

Data Index: 84585 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2567. Min Act: -0.0000

Data Index: 888089 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2977. Min Act: -0.0001

Data Index: 76103 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1216185 (C4 (Web Text))

Max Activating Token Index: 153