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

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

Neuron 2444 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.4400. Min Act: -0.0003

Data Index: 1444050 (Python Code)

Max Activating Token Index: 636

Text #1

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3718. Min Act: -0.0003

Data Index: 300432 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3496. Min Act: -0.0003

Data Index: 1430683 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3426. Min Act: -0.0003

Data Index: 1462490 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2783. Min Act: -0.0003

Data Index: 1597015 (Python Code)

Max Activating Token Index: 339

Text #5

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3199. Min Act: -0.0003

Data Index: 1413409 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3219. Min Act: -0.0003

Data Index: 1136109 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3140. Min Act: -0.0003

Data Index: 319199 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3126. Min Act: -0.0003

Data Index: 1129068 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3236. Min Act: -0.0003

Data Index: 1397886 (Python Code)

Max Activating Token Index: 510

Text #10

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2902. Min Act: -0.0003

Data Index: 950724 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3105. Min Act: -0.0003

Data Index: 1294716 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3287. Min Act: -0.0003

Data Index: 1409959 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3165. Min Act: -0.0003

Data Index: 653570 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2916. Min Act: -0.0003

Data Index: 1118222 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3367. Min Act: -0.0003

Data Index: 1457380 (Python Code)

Max Activating Token Index: 797

Text #16

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3025. Min Act: -0.0003

Data Index: 1374256 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3153. Min Act: -0.0003

Data Index: 1552026 (Python Code)

Max Activating Token Index: 838

Text #18

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3063. Min Act: -0.0003

Data Index: 1348241 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3252. Min Act: -0.0003

Data Index: 683951 (C4 (Web Text))

Max Activating Token Index: 56