Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1665 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1652524 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1477739 (Python Code)

Max Activating Token Index: 776

Text #2

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1640533 (Python Code)

Max Activating Token Index: 105

Text #3

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1431881 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1553928 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1646364 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1414902 (Python Code)

Max Activating Token Index: 903

Text #7

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1521668 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1382867 (Python Code)

Max Activating Token Index: 47

Text #9

Max Range: 1.3247. Min Range: -1.3247

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1555099 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1398832 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1381111 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1449656 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.9266. Min Act: -0.0001

Data Index: 1646942 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1543522 (Python Code)

Max Activating Token Index: 1020

Text #15

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1547902 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1652446 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1628596 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1526987 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 1.3247. Min Range: -1.3247

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1548875 (Python Code)

Max Activating Token Index: 983