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

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

Neuron 3317 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.9942. Min Act: -0.0001

Data Index: 1514963 (Python Code)

Max Activating Token Index: 753

Text #1

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.9722. Min Act: -0.0001

Data Index: 298051 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8061. Min Act: -0.0001

Data Index: 1627313 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8209. Min Act: -0.0001

Data Index: 1527510 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8876. Min Act: -0.0001

Data Index: 1484258 (Python Code)

Max Activating Token Index: 389

Text #5

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8310. Min Act: -0.0001

Data Index: 1608418 (Python Code)

Max Activating Token Index: 612

Text #6

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7751. Min Act: -0.0001

Data Index: 1124689 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7262. Min Act: -0.0001

Data Index: 1588239 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1505440 (Python Code)

Max Activating Token Index: 348

Text #9

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7654. Min Act: -0.0001

Data Index: 1390300 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7326. Min Act: -0.0001

Data Index: 1436995 (Python Code)

Max Activating Token Index: 440

Text #11

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7479. Min Act: -0.0001

Data Index: 122505 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.6157. Min Act: -0.0001

Data Index: 1501532 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.6095. Min Act: -0.0001

Data Index: 1518908 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1442432 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.6877. Min Act: -0.0001

Data Index: 1573657 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.8489. Min Act: -0.0001

Data Index: 246605 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.6956. Min Act: -0.0001

Data Index: 1598501 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.6592. Min Act: -0.0001

Data Index: 1615002 (Python Code)

Max Activating Token Index: 929

Text #19

Max Range: 0.9942. Min Range: -0.9942

Max Act: 0.7274. Min Act: -0.0001

Data Index: 1423326 (Python Code)

Max Activating Token Index: 898