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

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

Neuron 3972 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: 3.5964. Min Range: -3.5964

Max Act: 3.5964. Min Act: -0.0000

Data Index: 640479 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.9059. Min Act: -0.0001

Data Index: 747495 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.8836. Min Act: -0.0001

Data Index: 85261 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.8258. Min Act: -0.0000

Data Index: 821313 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.6705. Min Act: -0.0000

Data Index: 238981 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.5500. Min Act: -0.0000

Data Index: 420523 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.6713. Min Act: -0.0001

Data Index: 24868 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.7802. Min Act: -0.0000

Data Index: 76890 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.3086. Min Act: -0.0001

Data Index: 1059069 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.3428. Min Act: -0.0000

Data Index: 1128446 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.4633. Min Act: -0.0000

Data Index: 961618 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.4018. Min Act: -0.0000

Data Index: 163283 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.3705. Min Act: -0.0000

Data Index: 559885 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.2141. Min Act: -0.0000

Data Index: 740115 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.2342. Min Act: -0.0000

Data Index: 450675 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.1918. Min Act: -0.0001

Data Index: 938147 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.3065. Min Act: -0.0001

Data Index: 1347171 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.1874. Min Act: -0.0000

Data Index: 1113777 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 3.5964. Min Range: -3.5964

Max Act: 2.0782. Min Act: -0.0000

Data Index: 1317858 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.5964. Min Range: -3.5964

Max Act: 1.9766. Min Act: -0.0001

Data Index: 962230 (C4 (Web Text))

Max Activating Token Index: 729