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

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

Neuron 175 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: 0.1969. Min Range: -0.1969

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1535695 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1542903 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1633294 (Python Code)

Max Activating Token Index: 994

Text #3

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1590548 (Python Code)

Max Activating Token Index: 854

Text #4

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1375942 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1543393 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1377213 (Python Code)

Max Activating Token Index: 213

Text #7

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1511830 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1631401 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1492472 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1447868 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1407067 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1505950 (Python Code)

Max Activating Token Index: 788

Text #13

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1404800 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1478269 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1614031 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1633411 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1362544 (Python Code)

Max Activating Token Index: 157

Text #18

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1516311 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1462903 (Python Code)

Max Activating Token Index: 274