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

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

Neuron 230 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1388063 (Python Code)

Max Activating Token Index: 452

Text #1

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.3089. Min Act: -0.0001

Data Index: 1394412 (Python Code)

Max Activating Token Index: 300

Text #2

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2666. Min Act: -0.0001

Data Index: 1413036 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2734. Min Act: -0.0001

Data Index: 199710 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1127210 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2267. Min Act: -0.0001

Data Index: 286004 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2335. Min Act: -0.0001

Data Index: 887096 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2155. Min Act: -0.0001

Data Index: 243994 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1630755 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2172. Min Act: -0.0001

Data Index: 742160 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1396683 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1545156 (Python Code)

Max Activating Token Index: 296

Text #12

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2134. Min Act: -0.0001

Data Index: 215262 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1598725 (Python Code)

Max Activating Token Index: 429

Text #14

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2111. Min Act: -0.0001

Data Index: 362959 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.2037. Min Act: -0.0001

Data Index: 1641988 (Python Code)

Max Activating Token Index: 914

Text #16

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1550846 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1396856 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1415119 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 0.3089. Min Range: -0.3089

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1473821 (Python Code)

Max Activating Token Index: 101