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

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

Neuron 1566 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5471. Min Range: -3.5471

Max Act: 3.5471. Min Act: -0.0001

Data Index: 375563 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 3.5471. Min Range: -3.5471

Max Act: 3.0908. Min Act: -0.0001

Data Index: 1271636 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 3.5471. Min Range: -3.5471

Max Act: 3.0729. Min Act: -0.0001

Data Index: 1129440 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.5471. Min Range: -3.5471

Max Act: 3.0722. Min Act: -0.0001

Data Index: 683679 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.9110. Min Act: -0.0001

Data Index: 507284 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.5471. Min Range: -3.5471

Max Act: 3.0254. Min Act: -0.0001

Data Index: 162280 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.9876. Min Act: -0.0001

Data Index: 1219219 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.6938. Min Act: -0.0001

Data Index: 1061330 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.8271. Min Act: -0.0001

Data Index: 886543 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.9638. Min Act: -0.0001

Data Index: 441637 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.8988. Min Act: -0.0001

Data Index: 179250 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.8961. Min Act: -0.0001

Data Index: 59076 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.9522. Min Act: -0.0001

Data Index: 854756 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.7935. Min Act: -0.0001

Data Index: 484461 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.7847. Min Act: -0.0001

Data Index: 363149 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.7633. Min Act: -0.0001

Data Index: 473426 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 3.5471. Min Range: -3.5471

Max Act: 3.0243. Min Act: -0.0001

Data Index: 1322337 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.7302. Min Act: -0.0001

Data Index: 534153 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.5673. Min Act: -0.0001

Data Index: 43728 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 3.5471. Min Range: -3.5471

Max Act: 2.6011. Min Act: -0.0001

Data Index: 395392 (C4 (Web Text))

Max Activating Token Index: 649