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

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

Neuron 3451 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.7394. Min Act: -0.0000

Data Index: 793274 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.6115. Min Act: -0.0000

Data Index: 1286347 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.4096. Min Act: -0.0000

Data Index: 1065896 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.2336. Min Act: -0.0000

Data Index: 1022855 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.2470. Min Act: -0.0000

Data Index: 218855 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.4462. Min Act: -0.0000

Data Index: 880107 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.0922. Min Act: -0.0000

Data Index: 450475 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.0982. Min Act: -0.0000

Data Index: 85628 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.0924. Min Act: -0.0000

Data Index: 897992 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.0526. Min Act: -0.0000

Data Index: 791989 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.1890. Min Act: -0.0001

Data Index: 1146096 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 4.7394. Min Range: -4.7394

Max Act: 3.8882. Min Act: -0.0000

Data Index: 1133538 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 4.7394. Min Range: -4.7394

Max Act: 4.4229. Min Act: -0.0000

Data Index: 91895 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 4.7394. Min Range: -4.7394

Max Act: 3.9589. Min Act: -0.0000

Data Index: 738863 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 4.7394. Min Range: -4.7394

Max Act: 3.6976. Min Act: -0.0000

Data Index: 315670 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 4.7394. Min Range: -4.7394

Max Act: 3.8378. Min Act: -0.0000

Data Index: 1316196 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 4.7394. Min Range: -4.7394

Max Act: 3.5152. Min Act: -0.0000

Data Index: 1144935 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 4.7394. Min Range: -4.7394

Max Act: 3.7640. Min Act: -0.0000

Data Index: 68425 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 4.7394. Min Range: -4.7394

Max Act: 3.4309. Min Act: -0.0000

Data Index: 488622 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 4.7394. Min Range: -4.7394

Max Act: 3.4585. Min Act: -0.0001

Data Index: 1085239 (C4 (Web Text))

Max Activating Token Index: 957