Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4450 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1349956 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1073759 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1156674 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3802. Min Act: -0.0000

Data Index: 857791 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1591314 (Python Code)

Max Activating Token Index: 587

Text #5

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1277561 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1465188 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1437250 (Python Code)

Max Activating Token Index: 514

Text #8

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3829. Min Act: -0.0000

Data Index: 316483 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3183. Min Act: -0.0000

Data Index: 208217 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1414677 (Python Code)

Max Activating Token Index: 841

Text #11

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1590960 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1550081 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1105789 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3125. Min Act: -0.0000

Data Index: 810805 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1563941 (Python Code)

Max Activating Token Index: 555

Text #16

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.2859. Min Act: -0.0000

Data Index: 844138 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3035. Min Act: -0.0000

Data Index: 431212 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3111. Min Act: -0.0000

Data Index: 789723 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3423. Min Act: -0.0000

Data Index: 214565 (C4 (Web Text))

Max Activating Token Index: 829