Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 888 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0150. Min Range: -1.0150

Max Act: 1.0150. Min Act: -0.0002

Data Index: 491419 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8893. Min Act: -0.0001

Data Index: 800358 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 1.0150. Min Range: -1.0150

Max Act: 1.0141. Min Act: -0.0001

Data Index: 1100026 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 1.0150. Min Range: -1.0150

Max Act: 1.0076. Min Act: -0.0002

Data Index: 429764 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 1.0150. Min Range: -1.0150

Max Act: 1.0070. Min Act: -0.0002

Data Index: 107495 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.9502. Min Act: -0.0001

Data Index: 1133269 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 1.0150. Min Range: -1.0150

Max Act: 1.0129. Min Act: -0.0001

Data Index: 1250777 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8265. Min Act: -0.0001

Data Index: 1212922 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.9131. Min Act: -0.0002

Data Index: 850949 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8250. Min Act: -0.0001

Data Index: 443449 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.9365. Min Act: -0.0002

Data Index: 7424 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6714. Min Act: -0.0001

Data Index: 516417 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.9104. Min Act: -0.0001

Data Index: 392368 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8554. Min Act: -0.0002

Data Index: 1092415 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8463. Min Act: -0.0002

Data Index: 1127783 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8497. Min Act: -0.0001

Data Index: 7901 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8450. Min Act: -0.0002

Data Index: 1016990 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.7619. Min Act: -0.0002

Data Index: 1346237 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.8343. Min Act: -0.0001

Data Index: 1075434 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.7910. Min Act: -0.0001

Data Index: 554636 (C4 (Web Text))

Max Activating Token Index: 444