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

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

Neuron 544 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.7232. Min Act: -0.0001

Data Index: 845624 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1020436 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.4799. Min Act: -0.0000

Data Index: 51545 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.5743. Min Act: -0.0000

Data Index: 254009 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.2866. Min Act: -0.0001

Data Index: 871260 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.5218. Min Act: -0.0000

Data Index: 325001 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.3939. Min Act: -0.0000

Data Index: 908365 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.5036. Min Act: -0.0001

Data Index: 5294 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.2519. Min Act: -0.0000

Data Index: 5676 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.3566. Min Act: -0.0001

Data Index: 49105 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.3462. Min Act: -0.0001

Data Index: 702942 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.2955. Min Act: -0.0000

Data Index: 773217 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.2741. Min Act: -0.0000

Data Index: 1337172 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.0480. Min Act: -0.0001

Data Index: 496062 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.1364. Min Act: -0.0001

Data Index: 380294 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.0353. Min Act: -0.0001

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.0225. Min Act: -0.0001

Data Index: 971140 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.9095. Min Act: -0.0001

Data Index: 1052380 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.0067. Min Act: -0.0001

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.8781. Min Act: -0.0000

Data Index: 751549 (C4 (Web Text))

Max Activating Token Index: 592