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

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

Neuron 1372 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0453. Min Range: -1.0453

Max Act: 1.0453. Min Act: -0.0001

Data Index: 840952 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.8559. Min Act: -0.0001

Data Index: 455605 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.8965. Min Act: -0.0001

Data Index: 446203 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.8140. Min Act: -0.0001

Data Index: 1163317 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.7874. Min Act: -0.0001

Data Index: 1307490 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.8605. Min Act: -0.0000

Data Index: 778197 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.8150. Min Act: -0.0001

Data Index: 456220 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.7905. Min Act: -0.0001

Data Index: 410435 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1148122 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.7768. Min Act: -0.0001

Data Index: 859716 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.7329. Min Act: -0.0000

Data Index: 751186 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1118886 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.7070. Min Act: -0.0001

Data Index: 491742 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1207915 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.6993. Min Act: -0.0001

Data Index: 1146708 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.7176. Min Act: -0.0001

Data Index: 233579 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.7080. Min Act: -0.0001

Data Index: 244723 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.6785. Min Act: -0.0000

Data Index: 338488 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1292474 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.0453. Min Range: -1.0453

Max Act: 0.6863. Min Act: -0.0001

Data Index: 1082053 (C4 (Web Text))

Max Activating Token Index: 314