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

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

Neuron 1767 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2814. Min Act: -0.0000

Data Index: 791300 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.3093. Min Act: 0.0000

Data Index: 740152 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2869. Min Act: -0.0000

Data Index: 899957 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1286924 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1028913 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1242826 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2371. Min Act: -0.0000

Data Index: 73396 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1099510 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2417. Min Act: -0.0000

Data Index: 34418 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1241490 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2278. Min Act: -0.0000

Data Index: 85573 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2125. Min Act: -0.0000

Data Index: 335950 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2175. Min Act: -0.0000

Data Index: 404756 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2212. Min Act: -0.0000

Data Index: 549223 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1174147 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2154. Min Act: -0.0000

Data Index: 219647 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1947. Min Act: -0.0000

Data Index: 902188 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1937. Min Act: -0.0000

Data Index: 835221 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1313773 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1812. Min Act: -0.0000

Data Index: 157889 (C4 (Web Text))

Max Activating Token Index: 818