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

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

Neuron 3938 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.3058. Min Act: -0.0001

Data Index: 505513 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2359. Min Act: -0.0001

Data Index: 567128 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1999. Min Act: -0.0000

Data Index: 101969 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1966. Min Act: -0.0001

Data Index: 1209507 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1334. Min Act: -0.0000

Data Index: 973452 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1115341 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1267. Min Act: -0.0001

Data Index: 212777 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1351. Min Act: -0.0001

Data Index: 1332738 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1171. Min Act: -0.0001

Data Index: 147217 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1297. Min Act: -0.0001

Data Index: 252036 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1114532 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1141773 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1062. Min Act: -0.0001

Data Index: 987856 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1218513 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1028. Min Act: -0.0001

Data Index: 470431 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1062885 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1015. Min Act: -0.0001

Data Index: 292522 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1315907 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1471011 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1287951 (C4 (Web Text))

Max Activating Token Index: 817