Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3128 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0997. Min Range: -1.0997

Max Act: 1.0997. Min Act: -0.0001

Data Index: 1083101 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.9082. Min Act: -0.0001

Data Index: 1025210 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8450. Min Act: -0.0001

Data Index: 917228 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8650. Min Act: -0.0001

Data Index: 184953 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8423. Min Act: -0.0001

Data Index: 1059479 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8630. Min Act: -0.0001

Data Index: 706371 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.7872. Min Act: -0.0001

Data Index: 464094 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.7930. Min Act: -0.0001

Data Index: 1004227 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8139. Min Act: -0.0001

Data Index: 111662 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.7854. Min Act: -0.0001

Data Index: 1269452 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8751. Min Act: -0.0001

Data Index: 4808 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8313. Min Act: -0.0001

Data Index: 1225305 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8268. Min Act: -0.0001

Data Index: 62138 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.7771. Min Act: -0.0001

Data Index: 974988 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8520. Min Act: -0.0001

Data Index: 802849 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.8180. Min Act: -0.0001

Data Index: 894621 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.7913. Min Act: -0.0001

Data Index: 195109 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.7698. Min Act: -0.0001

Data Index: 1055200 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.7582. Min Act: -0.0001

Data Index: 743328 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.0997. Min Range: -1.0997

Max Act: 0.7590. Min Act: -0.0001

Data Index: 1117494 (C4 (Web Text))

Max Activating Token Index: 703