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

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

Neuron 1122 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.7910. Min Act: 0.0001

Data Index: 1990 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.7524. Min Act: 0.0001

Data Index: 255756 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1024593 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.4329. Min Act: -0.0000

Data Index: 373197 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.5085. Min Act: -0.0000

Data Index: 1162204 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1262573 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.4130. Min Act: -0.0000

Data Index: 567672 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.3089. Min Act: -0.0000

Data Index: 176257 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.3795. Min Act: -0.0000

Data Index: 411150 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.2851. Min Act: -0.0000

Data Index: 608677 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1067892 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.3504. Min Act: -0.0000

Data Index: 1062108 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.2702. Min Act: -0.0000

Data Index: 215645 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.3408. Min Act: 0.0000

Data Index: 382065 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.3134. Min Act: -0.0000

Data Index: 764826 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.3210. Min Act: 0.0001

Data Index: 1030830 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.2719. Min Act: -0.0000

Data Index: 147696 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.2075. Min Act: 0.0001

Data Index: 194184 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1300121 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.7910. Min Range: -1.7910

Max Act: 1.2416. Min Act: 0.0000

Data Index: 782826 (C4 (Web Text))

Max Activating Token Index: 433