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

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

Neuron 688 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0545. Min Range: -1.0545

Max Act: 1.0545. Min Act: -0.0001

Data Index: 929419 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.7605. Min Act: -0.0001

Data Index: 1137264 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9305. Min Act: -0.0001

Data Index: 265583 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9663. Min Act: -0.0001

Data Index: 318570 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8549. Min Act: -0.0001

Data Index: 282604 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8591. Min Act: -0.0001

Data Index: 903083 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8329. Min Act: -0.0001

Data Index: 143809 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8664. Min Act: -0.0001

Data Index: 955010 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8627. Min Act: -0.0001

Data Index: 294348 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8414. Min Act: -0.0001

Data Index: 212375 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8800. Min Act: -0.0001

Data Index: 486796 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8799. Min Act: -0.0001

Data Index: 49887 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9073. Min Act: -0.0001

Data Index: 1029939 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8726. Min Act: -0.0001

Data Index: 164382 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8490. Min Act: -0.0001

Data Index: 1448571 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.7395. Min Act: -0.0001

Data Index: 327093 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1321980 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8407. Min Act: -0.0001

Data Index: 678133 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.8343. Min Act: -0.0001

Data Index: 1298446 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 1.0545. Min Range: -1.0545

Max Act: 0.9057. Min Act: -0.0001

Data Index: 869683 (C4 (Web Text))

Max Activating Token Index: 469