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

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

Neuron 306 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.4288. Min Act: -0.0001

Data Index: 1132468 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.0544. Min Act: -0.0001

Data Index: 613149 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.3268. Min Act: -0.0001

Data Index: 1069782 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.1617. Min Act: -0.0001

Data Index: 1337505 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.7054. Min Act: -0.0001

Data Index: 1266039 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.1274. Min Act: -0.0001

Data Index: 290225 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.1030. Min Act: -0.0001

Data Index: 329653 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.1975. Min Act: -0.0001

Data Index: 1348726 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.0288. Min Act: -0.0001

Data Index: 821987 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.9334. Min Act: -0.0001

Data Index: 381200 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.8019. Min Act: -0.0001

Data Index: 1219990 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.7332. Min Act: -0.0001

Data Index: 902334 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.8587. Min Act: -0.0001

Data Index: 634627 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.9837. Min Act: -0.0001

Data Index: 1309360 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.7014. Min Act: -0.0001

Data Index: 800744 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.4891. Min Act: -0.0001

Data Index: 592307 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 3.4288. Min Range: -3.4288

Max Act: 3.0223. Min Act: -0.0001

Data Index: 1028179 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.9080. Min Act: -0.0001

Data Index: 418651 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.8148. Min Act: -0.0001

Data Index: 592705 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 3.4288. Min Range: -3.4288

Max Act: 2.7705. Min Act: -0.0001

Data Index: 775496 (C4 (Web Text))

Max Activating Token Index: 738