Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2176 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2919. Min Act: -0.0001

Data Index: 1175478 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2434. Min Act: -0.0001

Data Index: 1316503 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2412. Min Act: -0.0001

Data Index: 875542 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2328. Min Act: -0.0001

Data Index: 427924 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2286. Min Act: -0.0001

Data Index: 704130 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2158. Min Act: -0.0001

Data Index: 347592 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1005746 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2042. Min Act: -0.0001

Data Index: 656824 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2103. Min Act: -0.0001

Data Index: 228970 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1943. Min Act: -0.0001

Data Index: 222791 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1908. Min Act: -0.0001

Data Index: 683927 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1115332 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1064127 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1965. Min Act: -0.0001

Data Index: 440623 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2002. Min Act: -0.0001

Data Index: 882670 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1949. Min Act: -0.0001

Data Index: 9053 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1177671 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1869. Min Act: -0.0001

Data Index: 773827 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2060. Min Act: -0.0001

Data Index: 1344074 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2048. Min Act: -0.0001

Data Index: 599464 (C4 (Web Text))

Max Activating Token Index: 157