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

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

Neuron 3190 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: 0.8034. Min Range: -0.8034

Max Act: 0.8034. Min Act: -0.0000

Data Index: 835189 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.5699. Min Act: -0.0000

Data Index: 265976 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6285. Min Act: -0.0001

Data Index: 1336864 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.6056. Min Act: -0.0000

Data Index: 822468 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.5861. Min Act: -0.0000

Data Index: 297764 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.5894. Min Act: -0.0000

Data Index: 629506 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.5541. Min Act: -0.0000

Data Index: 791996 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.5304. Min Act: -0.0000

Data Index: 227236 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4834. Min Act: -0.0001

Data Index: 559175 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.5248. Min Act: -0.0000

Data Index: 747881 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.5586. Min Act: -0.0001

Data Index: 551616 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4918. Min Act: -0.0000

Data Index: 908572 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4862. Min Act: -0.0001

Data Index: 341056 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4802. Min Act: -0.0000

Data Index: 424476 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.5021. Min Act: -0.0000

Data Index: 442072 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4642. Min Act: -0.0000

Data Index: 370129 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4820. Min Act: -0.0001

Data Index: 65180 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4723. Min Act: -0.0001

Data Index: 993440 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4911. Min Act: -0.0000

Data Index: 744289 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.8034. Min Range: -0.8034

Max Act: 0.4899. Min Act: -0.0000

Data Index: 695998 (C4 (Web Text))

Max Activating Token Index: 56