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

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

Neuron 2161 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.4741. Min Act: -0.0000

Data Index: 807253 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1358860 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1325614 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.1118. Min Act: -0.0000

Data Index: 306082 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.0329. Min Act: -0.0000

Data Index: 538333 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1161567 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.0133. Min Act: -0.0000

Data Index: 350941 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1347234 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.8893. Min Act: -0.0000

Data Index: 121067 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1034225 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.9910. Min Act: -0.0000

Data Index: 129459 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.8356. Min Act: -0.0000

Data Index: 344963 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.4741. Min Range: -1.4741

Max Act: 1.0033. Min Act: -0.0000

Data Index: 167058 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1472935 (Python Code)

Max Activating Token Index: 584

Text #14

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.8544. Min Act: -0.0000

Data Index: 513762 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.8610. Min Act: -0.0000

Data Index: 576490 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1045911 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.8177. Min Act: -0.0000

Data Index: 491419 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1528345 (Python Code)

Max Activating Token Index: 598

Text #19

Max Range: 1.4741. Min Range: -1.4741

Max Act: 0.7784. Min Act: -0.0000

Data Index: 781207 (C4 (Web Text))

Max Activating Token Index: 560