Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4865 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 215276 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0002

Data Index: 444468 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0002

Data Index: 386345 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0002

Data Index: 849623 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1228461 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0049. Min Act: -0.0002

Data Index: 378531 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0002

Data Index: 377910 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0049. Min Act: -0.0002

Data Index: 111582 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0050. Min Act: -0.0002

Data Index: 911901 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0002

Data Index: 524050 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1140221 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0050. Min Act: -0.0003

Data Index: 707732 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0047. Min Act: -0.0002

Data Index: 12341 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0042. Min Act: -0.0002

Data Index: 418257 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0041. Min Act: -0.0002

Data Index: 1224718 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0047. Min Act: -0.0002

Data Index: 483980 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0050. Min Act: -0.0002

Data Index: 627880 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0044. Min Act: -0.0002

Data Index: 586914 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1093099 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0049. Min Act: -0.0002

Data Index: 281988 (C4 (Web Text))

Max Activating Token Index: 827