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

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

Neuron 1203 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0240. Min Range: -1.0240

Max Act: 1.0240. Min Act: 0.0001

Data Index: 226692 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.9856. Min Act: -0.0000

Data Index: 761753 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.9275. Min Act: -0.0000

Data Index: 136296 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.9662. Min Act: -0.0000

Data Index: 769535 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.9023. Min Act: 0.0000

Data Index: 1228772 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.8503. Min Act: 0.0001

Data Index: 662174 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.8318. Min Act: -0.0000

Data Index: 840313 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.8325. Min Act: -0.0000

Data Index: 193991 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.8076. Min Act: 0.0001

Data Index: 795855 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7996. Min Act: 0.0001

Data Index: 938113 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1090608 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7622. Min Act: -0.0000

Data Index: 595967 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7734. Min Act: 0.0001

Data Index: 1148317 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7857. Min Act: -0.0000

Data Index: 749562 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7522. Min Act: 0.0001

Data Index: 1305578 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7957. Min Act: -0.0000

Data Index: 46948 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7636. Min Act: -0.0000

Data Index: 276164 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7115. Min Act: 0.0001

Data Index: 416248 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7389. Min Act: 0.0001

Data Index: 583073 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7181. Min Act: -0.0000

Data Index: 795745 (C4 (Web Text))

Max Activating Token Index: 872