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

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

Neuron 4325 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1986. Min Act: -0.0000

Data Index: 875948 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0881. Min Act: -0.0000

Data Index: 711086 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.1714. Min Act: -0.0000

Data Index: 206310 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0895. Min Act: -0.0000

Data Index: 749441 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9912. Min Act: -0.0000

Data Index: 929846 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 1.1986. Min Range: -1.1986

Max Act: 1.0305. Min Act: -0.0000

Data Index: 209002 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.8858. Min Act: -0.0000

Data Index: 297422 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.8958. Min Act: -0.0000

Data Index: 57115 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1072795 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9126. Min Act: -0.0000

Data Index: 191652 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9061. Min Act: -0.0000

Data Index: 93179 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.6952. Min Act: -0.0000

Data Index: 151094 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9099. Min Act: -0.0000

Data Index: 335474 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.8199. Min Act: -0.0000

Data Index: 473212 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.9202. Min Act: -0.0000

Data Index: 10358 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.8023. Min Act: -0.0000

Data Index: 7529 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1041348 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.7589. Min Act: -0.0000

Data Index: 804353 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1013449 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.1986. Min Range: -1.1986

Max Act: 0.7668. Min Act: -0.0000

Data Index: 106794 (C4 (Web Text))

Max Activating Token Index: 640