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

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

Neuron 2393 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.7649. Min Act: -0.0001

Data Index: 1235357 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 4.2437. Min Range: -4.2437

Max Act: 4.2437. Min Act: -0.0001

Data Index: 1010092 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.6381. Min Act: -0.0001

Data Index: 797656 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.7465. Min Act: -0.0000

Data Index: 625840 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.8326. Min Act: -0.0001

Data Index: 1073101 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.9533. Min Act: -0.0001

Data Index: 795095 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.5146. Min Act: -0.0000

Data Index: 152258 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 4.2437. Min Range: -4.2437

Max Act: 4.0492. Min Act: -0.0001

Data Index: 1325102 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.5978. Min Act: -0.0001

Data Index: 52245 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.4139. Min Act: -0.0001

Data Index: 308139 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.4953. Min Act: -0.0000

Data Index: 652974 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.3335. Min Act: -0.0001

Data Index: 387390 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.2040. Min Act: -0.0001

Data Index: 732727 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.1174. Min Act: -0.0001

Data Index: 67210 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.1101. Min Act: -0.0001

Data Index: 704565 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.0679. Min Act: -0.0001

Data Index: 1261749 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.2458. Min Act: -0.0001

Data Index: 784839 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.0892. Min Act: -0.0001

Data Index: 1306926 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.2171. Min Act: -0.0001

Data Index: 1181762 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 4.2437. Min Range: -4.2437

Max Act: 3.3586. Min Act: -0.0001

Data Index: 1149938 (C4 (Web Text))

Max Activating Token Index: 168