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

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

Neuron 827 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: 0.6478. Min Range: -0.6478

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1603997 (Python Code)

Max Activating Token Index: 915

Text #1

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.6478. Min Act: -0.0000

Data Index: 606753 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1399599 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5150. Min Act: -0.0000

Data Index: 651997 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1256611 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1361111 (Python Code)

Max Activating Token Index: 487

Text #6

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4584. Min Act: -0.0000

Data Index: 173621 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1004061 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1050646 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4494. Min Act: -0.0000

Data Index: 452903 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1216574 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4335. Min Act: -0.0000

Data Index: 125740 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4179. Min Act: -0.0000

Data Index: 13985 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4252. Min Act: -0.0000

Data Index: 221225 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4408. Min Act: -0.0000

Data Index: 419415 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4331. Min Act: -0.0000

Data Index: 839139 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4587. Min Act: -0.0000

Data Index: 564961 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4422. Min Act: -0.0000

Data Index: 747890 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1097885 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.6478. Min Range: -0.6478

Max Act: 0.4288. Min Act: -0.0000

Data Index: 785977 (C4 (Web Text))

Max Activating Token Index: 789