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

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

Neuron 201 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.6540. Min Act: -0.0000

Data Index: 550153 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.4274. Min Act: -0.0000

Data Index: 269022 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.3637. Min Act: -0.0000

Data Index: 1152705 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.3276. Min Act: -0.0000

Data Index: 516264 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.3963. Min Act: -0.0000

Data Index: 380978 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.1761. Min Act: -0.0000

Data Index: 474595 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.2866. Min Act: -0.0000

Data Index: 57299 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.2368. Min Act: -0.0001

Data Index: 1600457 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.2445. Min Act: -0.0000

Data Index: 1038022 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.3157. Min Act: -0.0000

Data Index: 440550 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.2775. Min Act: -0.0000

Data Index: 372562 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1162408 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.2331. Min Act: -0.0000

Data Index: 504435 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0929. Min Act: -0.0001

Data Index: 1620143 (Python Code)

Max Activating Token Index: 797

Text #14

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.1945. Min Act: -0.0001

Data Index: 1538329 (Python Code)

Max Activating Token Index: 321

Text #15

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.1887. Min Act: -0.0000

Data Index: 735720 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.2287. Min Act: -0.0000

Data Index: 686692 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.0919. Min Act: -0.0000

Data Index: 688007 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.1260. Min Act: -0.0000

Data Index: 300942 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 1.6540. Min Range: -1.6540

Max Act: 1.1705. Min Act: -0.0000

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 483