Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 535 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.8787. Min Act: -0.0000

Data Index: 181155 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.7128. Min Act: -0.0000

Data Index: 346359 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1281237 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6456. Min Act: -0.0000

Data Index: 383188 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1146302 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6058. Min Act: -0.0000

Data Index: 734219 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.6402. Min Act: -0.0000

Data Index: 697311 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5542. Min Act: -0.0000

Data Index: 70242 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5743. Min Act: -0.0000

Data Index: 688134 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5892. Min Act: -0.0000

Data Index: 840646 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5764. Min Act: -0.0000

Data Index: 53356 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1089465 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5679. Min Act: -0.0000

Data Index: 182782 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5339. Min Act: -0.0000

Data Index: 511004 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5657. Min Act: -0.0000

Data Index: 574261 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5325. Min Act: -0.0000

Data Index: 403014 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5288. Min Act: -0.0000

Data Index: 255505 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5120. Min Act: -0.0000

Data Index: 197218 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1142741 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.8787. Min Range: -0.8787

Max Act: 0.5265. Min Act: -0.0000

Data Index: 150878 (C4 (Web Text))

Max Activating Token Index: 656