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

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

Neuron 1355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1141527 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2615. Min Act: -0.0000

Data Index: 661870 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2384. Min Act: -0.0000

Data Index: 316277 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2371. Min Act: -0.0000

Data Index: 953678 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1086664 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2192. Min Act: -0.0000

Data Index: 822533 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1204333 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1298633 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1154795 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1323105 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2191. Min Act: -0.0001

Data Index: 800783 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1407213 (Python Code)

Max Activating Token Index: 709

Text #12

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1513046 (Python Code)

Max Activating Token Index: 255

Text #13

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1314489 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2145. Min Act: -0.0000

Data Index: 332906 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1185709 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2280. Min Act: -0.0000

Data Index: 925370 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2178. Min Act: -0.0001

Data Index: 432360 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2104. Min Act: -0.0001

Data Index: 442847 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.2715. Min Range: -0.2715

Max Act: 0.2081. Min Act: -0.0001

Data Index: 25650 (C4 (Web Text))

Max Activating Token Index: 334