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

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

Neuron 129 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6548. Min Range: -4.6548

Max Act: 4.6548. Min Act: -0.0000

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 4.6548. Min Range: -4.6548

Max Act: 4.1081. Min Act: -0.0000

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 4.6548. Min Range: -4.6548

Max Act: 4.1207. Min Act: -0.0000

Data Index: 632553 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 4.6548. Min Range: -4.6548

Max Act: 4.2132. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.6548. Min Range: -4.6548

Max Act: 4.0450. Min Act: -0.0000

Data Index: 1193778 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.8805. Min Act: -0.0000

Data Index: 176465 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.4943. Min Act: -0.0000

Data Index: 753187 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.0411. Min Act: -0.0000

Data Index: 857647 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.4955. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.2579. Min Act: -0.0000

Data Index: 25708 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.1484. Min Act: -0.0000

Data Index: 136362 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.5175. Min Act: -0.0000

Data Index: 343043 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.1459. Min Act: -0.0000

Data Index: 1347006 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.2980. Min Act: -0.0000

Data Index: 578975 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.3994. Min Act: -0.0000

Data Index: 277531 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.0912. Min Act: -0.0000

Data Index: 265198 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.4075. Min Act: -0.0000

Data Index: 1261156 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 4.6548. Min Range: -4.6548

Max Act: 2.9373. Min Act: -0.0000

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 4.6548. Min Range: -4.6548

Max Act: 3.2212. Min Act: -0.0000

Data Index: 1310054 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 4.6548. Min Range: -4.6548

Max Act: 2.7591. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 998