Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1041 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4974. Min Act: -0.0001

Data Index: 1344829 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4079. Min Act: -0.0001

Data Index: 71811 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.2936. Min Act: -0.0001

Data Index: 1537071 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.4045. Min Act: -0.0001

Data Index: 723800 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3560. Min Act: -0.0001

Data Index: 666321 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3712. Min Act: -0.0001

Data Index: 1567007 (Python Code)

Max Activating Token Index: 158

Text #6

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.2537. Min Act: -0.0001

Data Index: 1335216 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.2494. Min Act: -0.0001

Data Index: 1477659 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.2001. Min Act: -0.0001

Data Index: 218767 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.2066. Min Act: -0.0001

Data Index: 1517623 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1252. Min Act: -0.0001

Data Index: 298347 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.3143. Min Act: -0.0001

Data Index: 628039 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.2042. Min Act: -0.0001

Data Index: 1653442 (Python Code)

Max Activating Token Index: 948

Text #13

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1781. Min Act: -0.0001

Data Index: 1497301 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1998. Min Act: -0.0001

Data Index: 804191 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1198. Min Act: -0.0001

Data Index: 1051048 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1553. Min Act: -0.0001

Data Index: 717534 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1422. Min Act: -0.0001

Data Index: 1428414 (Python Code)

Max Activating Token Index: 1015

Text #18

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1462. Min Act: -0.0001

Data Index: 1484589 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 1.4974. Min Range: -1.4974

Max Act: 1.1657. Min Act: -0.0001

Data Index: 1454562 (Python Code)

Max Activating Token Index: 514