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

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

Neuron 75 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0489. Min Range: -1.0489

Max Act: 1.0489. Min Act: -0.0001

Data Index: 736615 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.9547. Min Act: -0.0001

Data Index: 1191066 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.9077. Min Act: -0.0001

Data Index: 1058518 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8502. Min Act: -0.0001

Data Index: 256577 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8931. Min Act: -0.0001

Data Index: 109096 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.9062. Min Act: -0.0001

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8575. Min Act: -0.0001

Data Index: 159195 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8305. Min Act: -0.0001

Data Index: 479526 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8263. Min Act: -0.0001

Data Index: 104175 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8161. Min Act: -0.0001

Data Index: 1285002 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8075. Min Act: -0.0001

Data Index: 914626 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8248. Min Act: -0.0001

Data Index: 1122563 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7388. Min Act: -0.0001

Data Index: 186636 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7855. Min Act: -0.0001

Data Index: 98277 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.8091. Min Act: -0.0001

Data Index: 23752 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7832. Min Act: -0.0001

Data Index: 1183871 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7303. Min Act: -0.0001

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7562. Min Act: -0.0001

Data Index: 1264565 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.0489. Min Range: -1.0489

Max Act: 0.7718. Min Act: -0.0001

Data Index: 368146 (C4 (Web Text))

Max Activating Token Index: 155