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

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

Neuron 3222 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.5771. Min Act: -0.0001

Data Index: 1463568 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.5707. Min Act: -0.0001

Data Index: 1532431 (Python Code)

Max Activating Token Index: 958

Text #2

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4972. Min Act: -0.0001

Data Index: 1629569 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.5265. Min Act: -0.0001

Data Index: 1388274 (Python Code)

Max Activating Token Index: 222

Text #4

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4712. Min Act: -0.0001

Data Index: 338020 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4380. Min Act: -0.0001

Data Index: 1639274 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1593940 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1461833 (Python Code)

Max Activating Token Index: 577

Text #8

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3939. Min Act: -0.0001

Data Index: 1519335 (Python Code)

Max Activating Token Index: 480

Text #9

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4075. Min Act: -0.0001

Data Index: 1472936 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3939. Min Act: -0.0001

Data Index: 1440146 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4021. Min Act: -0.0001

Data Index: 1380166 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3812. Min Act: -0.0001

Data Index: 1363026 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3983. Min Act: -0.0001

Data Index: 1405709 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3871. Min Act: -0.0001

Data Index: 966092 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3715. Min Act: -0.0001

Data Index: 1451488 (Python Code)

Max Activating Token Index: 509

Text #16

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3957. Min Act: -0.0001

Data Index: 952417 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3853. Min Act: -0.0001

Data Index: 1100655 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.4079. Min Act: -0.0001

Data Index: 1519196 (Python Code)

Max Activating Token Index: 178

Text #19

Max Range: 0.5771. Min Range: -0.5771

Max Act: 0.3657. Min Act: -0.0001

Data Index: 1583151 (Python Code)

Max Activating Token Index: 246