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

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

Neuron 5457 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: 4.0670. Min Range: -4.0670

Max Act: 4.0670. Min Act: -0.0001

Data Index: 754295 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.6562. Min Act: -0.0001

Data Index: 1114247 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.5624. Min Act: -0.0000

Data Index: 191846 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.5186. Min Act: -0.0001

Data Index: 1026528 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.2932. Min Act: -0.0000

Data Index: 1024348 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.4654. Min Act: -0.0001

Data Index: 769022 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.5590. Min Act: -0.0000

Data Index: 273386 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.4213. Min Act: -0.0000

Data Index: 36817 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.5276. Min Act: -0.0000

Data Index: 1193036 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.4818. Min Act: -0.0000

Data Index: 147373 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.2295. Min Act: -0.0000

Data Index: 308070 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.4389. Min Act: -0.0000

Data Index: 98728 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.2110. Min Act: -0.0000

Data Index: 219909 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.2787. Min Act: -0.0001

Data Index: 1301198 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.2105. Min Act: -0.0000

Data Index: 592602 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.2094. Min Act: -0.0000

Data Index: 1030892 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.2142. Min Act: -0.0001

Data Index: 295893 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.2014. Min Act: -0.0000

Data Index: 465469 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.1361. Min Act: -0.0001

Data Index: 19676 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 4.0670. Min Range: -4.0670

Max Act: 2.3166. Min Act: -0.0001

Data Index: 280658 (C4 (Web Text))

Max Activating Token Index: 986