Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 959 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.7035. Min Act: -0.0001

Data Index: 325421 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.5583. Min Act: -0.0001

Data Index: 229124 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.5099. Min Act: -0.0001

Data Index: 579644 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.5025. Min Act: -0.0001

Data Index: 480244 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4805. Min Act: -0.0001

Data Index: 1037267 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1284522 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4773. Min Act: -0.0001

Data Index: 771316 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4593. Min Act: -0.0001

Data Index: 923135 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4464. Min Act: -0.0001

Data Index: 746350 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4510. Min Act: -0.0001

Data Index: 794958 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4319. Min Act: -0.0001

Data Index: 326869 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4473. Min Act: -0.0001

Data Index: 837780 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4582. Min Act: -0.0001

Data Index: 606221 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4567. Min Act: -0.0001

Data Index: 307900 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4012. Min Act: -0.0001

Data Index: 643873 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4314. Min Act: -0.0001

Data Index: 500071 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4211. Min Act: -0.0001

Data Index: 642621 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4086. Min Act: -0.0001

Data Index: 1156686 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.3795. Min Act: -0.0001

Data Index: 249254 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4495. Min Act: -0.0001

Data Index: 685002 (C4 (Web Text))

Max Activating Token Index: 424