Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 650 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0936. Min Range: -2.0936

Max Act: 2.0851. Min Act: -0.0000

Data Index: 1140476 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 2.0936. Min Range: -2.0936

Max Act: 2.0936. Min Act: 0.0000

Data Index: 115755 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.9286. Min Act: -0.0000

Data Index: 980007 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.9002. Min Act: -0.0000

Data Index: 949778 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.6771. Min Act: -0.0000

Data Index: 1018593 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.5572. Min Act: -0.0000

Data Index: 1261601 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.5100. Min Act: -0.0000

Data Index: 590483 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.4966. Min Act: -0.0000

Data Index: 152968 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.4747. Min Act: -0.0000

Data Index: 83461 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1354246 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.4238. Min Act: -0.0000

Data Index: 230778 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.4037. Min Act: -0.0000

Data Index: 1278344 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.3553. Min Act: -0.0000

Data Index: 871753 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.2562. Min Act: -0.0000

Data Index: 539062 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1160032 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1236274 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1336269 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1213833 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 2.0936. Min Range: -2.0936

Max Act: 1.2643. Min Act: -0.0000

Data Index: 183836 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 2.0936. Min Range: -2.0936

Max Act: 0.9462. Min Act: -0.0000

Data Index: 821054 (C4 (Web Text))

Max Activating Token Index: 769