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

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

Neuron 90 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1529089 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1413791 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1435933 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1502180 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1486742 (Python Code)

Max Activating Token Index: 450

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1599172 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1611846 (Python Code)

Max Activating Token Index: 975

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1508511 (Python Code)

Max Activating Token Index: 533

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1640625 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1514882 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1462863 (Python Code)

Max Activating Token Index: 524

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1454052 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1469225 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1007. Min Act: -0.0001

Data Index: 429735 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1425480 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1032. Min Act: -0.0001

Data Index: 231020 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0952. Min Act: -0.0001

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1555102 (Python Code)

Max Activating Token Index: 492

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1650919 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1505543 (Python Code)

Max Activating Token Index: 489