Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4861 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.7213. Min Act: -0.0000

Data Index: 818957 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6507. Min Act: -0.0000

Data Index: 631579 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1027908 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1039802 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5370. Min Act: -0.0000

Data Index: 838764 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.5681. Min Act: -0.0000

Data Index: 244180 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4605. Min Act: -0.0000

Data Index: 852582 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4559. Min Act: -0.0000

Data Index: 829500 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4856. Min Act: -0.0000

Data Index: 730026 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4114. Min Act: -0.0000

Data Index: 627384 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4705. Min Act: -0.0000

Data Index: 796371 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1162229 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1250087 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1209931 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.3989. Min Act: -0.0000

Data Index: 334068 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4176. Min Act: -0.0000

Data Index: 234868 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1134786 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4125. Min Act: -0.0000

Data Index: 318261 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4083. Min Act: -0.0000

Data Index: 792575 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.7213. Min Range: -0.7213

Max Act: 0.4042. Min Act: -0.0000

Data Index: 689932 (C4 (Web Text))

Max Activating Token Index: 784