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

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

Neuron 5522 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2680. Min Act: -0.0000

Data Index: 105162 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1211256 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2422. Min Act: -0.0000

Data Index: 747568 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2547. Min Act: -0.0000

Data Index: 10211 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1192825 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2227. Min Act: -0.0000

Data Index: 399620 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2217. Min Act: -0.0000

Data Index: 390838 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1242056 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2057. Min Act: -0.0000

Data Index: 987223 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1127445 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2168. Min Act: -0.0000

Data Index: 969524 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2077. Min Act: -0.0000

Data Index: 94758 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1191212 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1992. Min Act: -0.0000

Data Index: 156722 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2040. Min Act: -0.0000

Data Index: 138099 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1872. Min Act: -0.0000

Data Index: 694054 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1955. Min Act: -0.0000

Data Index: 160943 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1225035 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2004. Min Act: -0.0000

Data Index: 659411 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2027. Min Act: -0.0000

Data Index: 828879 (C4 (Web Text))

Max Activating Token Index: 522