Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3164 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1641. Min Act: -0.0000

Data Index: 998027 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1368. Min Act: -0.0000

Data Index: 649165 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1089172 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1327. Min Act: -0.0000

Data Index: 400892 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1313. Min Act: -0.0001

Data Index: 475080 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1348363 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1103. Min Act: -0.0000

Data Index: 915584 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1354727 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1043834 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1070. Min Act: -0.0001

Data Index: 526858 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1263151 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0987. Min Act: -0.0000

Data Index: 437012 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0943. Min Act: 0.0001

Data Index: 145700 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0973. Min Act: -0.0000

Data Index: 358173 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1180007 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0944. Min Act: -0.0001

Data Index: 976196 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1127464 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0960. Min Act: 0.0001

Data Index: 619337 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0956. Min Act: -0.0001

Data Index: 585948 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1275902 (C4 (Web Text))

Max Activating Token Index: 461