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

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

Neuron 1918 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0668. Min Range: -1.0668

Max Act: 1.0083. Min Act: -0.0001

Data Index: 1228832 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 1.0668. Min Range: -1.0668

Max Act: 1.0006. Min Act: -0.0001

Data Index: 794289 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9603. Min Act: -0.0001

Data Index: 619087 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.0668. Min Range: -1.0668

Max Act: 1.0293. Min Act: -0.0001

Data Index: 212922 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.0668. Min Range: -1.0668

Max Act: 1.0668. Min Act: -0.0001

Data Index: 19480 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9514. Min Act: -0.0001

Data Index: 173332 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9196. Min Act: -0.0000

Data Index: 250174 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1097593 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1353584 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9359. Min Act: -0.0000

Data Index: 773241 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9137. Min Act: -0.0001

Data Index: 324261 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8839. Min Act: -0.0001

Data Index: 19229 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8992. Min Act: -0.0000

Data Index: 779629 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1002781 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8949. Min Act: -0.0001

Data Index: 514115 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.9065. Min Act: -0.0000

Data Index: 349030 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8524. Min Act: -0.0000

Data Index: 455396 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1168800 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1312074 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.0668. Min Range: -1.0668

Max Act: 0.8438. Min Act: -0.0000

Data Index: 42985 (C4 (Web Text))

Max Activating Token Index: 126