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

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

Neuron 1252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.4646. Min Range: -9.4646

Max Act: 9.4646. Min Act: -0.0001

Data Index: 871990 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 9.4646. Min Range: -9.4646

Max Act: 9.0221. Min Act: -0.0000

Data Index: 117046 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 9.4646. Min Range: -9.4646

Max Act: 8.6774. Min Act: -0.0000

Data Index: 1319157 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 9.4646. Min Range: -9.4646

Max Act: 8.0689. Min Act: -0.0001

Data Index: 129138 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 9.4646. Min Range: -9.4646

Max Act: 8.5857. Min Act: -0.0000

Data Index: 372228 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 9.4646. Min Range: -9.4646

Max Act: 9.4376. Min Act: -0.0001

Data Index: 1150197 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 9.4646. Min Range: -9.4646

Max Act: 8.7056. Min Act: -0.0000

Data Index: 595710 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 9.4646. Min Range: -9.4646

Max Act: 8.4052. Min Act: -0.0001

Data Index: 901983 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 9.4646. Min Range: -9.4646

Max Act: 8.6096. Min Act: -0.0001

Data Index: 1014276 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 9.4646. Min Range: -9.4646

Max Act: 7.8856. Min Act: -0.0001

Data Index: 677687 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 9.4646. Min Range: -9.4646

Max Act: 7.5965. Min Act: -0.0001

Data Index: 413796 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 9.4646. Min Range: -9.4646

Max Act: 6.4252. Min Act: -0.0001

Data Index: 380403 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 9.4646. Min Range: -9.4646

Max Act: 6.8411. Min Act: -0.0000

Data Index: 141453 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 9.4646. Min Range: -9.4646

Max Act: 7.1590. Min Act: -0.0001

Data Index: 528332 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 9.4646. Min Range: -9.4646

Max Act: 5.9967. Min Act: -0.0000

Data Index: 810263 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 9.4646. Min Range: -9.4646

Max Act: 6.8640. Min Act: -0.0000

Data Index: 1168214 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 9.4646. Min Range: -9.4646

Max Act: 6.2562. Min Act: -0.0001

Data Index: 210975 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 9.4646. Min Range: -9.4646

Max Act: 7.2318. Min Act: -0.0001

Data Index: 1215806 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 9.4646. Min Range: -9.4646

Max Act: 5.5910. Min Act: -0.0000

Data Index: 319985 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 9.4646. Min Range: -9.4646

Max Act: 4.6785. Min Act: -0.0001

Data Index: 713460 (C4 (Web Text))

Max Activating Token Index: 672