Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3000 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.5212. Min Act: -0.0000

Data Index: 20879 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3717. Min Act: -0.0000

Data Index: 92751 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3304. Min Act: -0.0000

Data Index: 860197 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1263663 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2970. Min Act: -0.0000

Data Index: 280981 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3003. Min Act: 0.0000

Data Index: 1206262 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3073. Min Act: -0.0000

Data Index: 448623 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2900. Min Act: -0.0000

Data Index: 406090 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3014. Min Act: -0.0000

Data Index: 269243 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1110651 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2792. Min Act: -0.0000

Data Index: 501620 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2865. Min Act: -0.0000

Data Index: 101382 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1163791 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2724. Min Act: -0.0000

Data Index: 751445 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1269158 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2920. Min Act: -0.0000

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2816. Min Act: 0.0000

Data Index: 632751 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2702. Min Act: -0.0000

Data Index: 371244 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2782. Min Act: -0.0000

Data Index: 407051 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.2690. Min Act: -0.0000

Data Index: 471330 (C4 (Web Text))

Max Activating Token Index: 612