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

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

Neuron 3916 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0001

Data Index: 825247 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1016. Min Act: -0.0001

Data Index: 257806 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1018. Min Act: -0.0001

Data Index: 11256 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0943. Min Act: -0.0001

Data Index: 38650 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1564063 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1555895 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0810. Min Act: -0.0001

Data Index: 474703 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0736. Min Act: -0.0001

Data Index: 14868 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1336561 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0812. Min Act: -0.0001

Data Index: 534824 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0802. Min Act: -0.0001

Data Index: 176248 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0743. Min Act: -0.0001

Data Index: 723921 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0792. Min Act: -0.0001

Data Index: 553131 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0823. Min Act: -0.0001

Data Index: 864971 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0822. Min Act: -0.0001

Data Index: 848628 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0794. Min Act: -0.0001

Data Index: 313486 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0715. Min Act: -0.0001

Data Index: 134043 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0807. Min Act: -0.0001

Data Index: 712350 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0729. Min Act: -0.0001

Data Index: 440186 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0776. Min Act: -0.0001

Data Index: 729784 (C4 (Web Text))

Max Activating Token Index: 566