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

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

Neuron 1704 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.3394. Min Act: -0.0000

Data Index: 832058 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0148. Min Act: -0.0000

Data Index: 685458 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0552. Min Act: -0.0000

Data Index: 191097 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1296066 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0651. Min Act: -0.0000

Data Index: 352156 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.8903. Min Act: -0.0000

Data Index: 578299 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1158516 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.8296. Min Act: -0.0000

Data Index: 660905 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.8054. Min Act: -0.0000

Data Index: 307034 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.7974. Min Act: -0.0000

Data Index: 792194 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.7071. Min Act: -0.0000

Data Index: 128049 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.6581. Min Act: -0.0000

Data Index: 378092 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.6687. Min Act: -0.0000

Data Index: 839455 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.7151. Min Act: -0.0000

Data Index: 875382 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.6899. Min Act: -0.0000

Data Index: 113863 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.6399. Min Act: -0.0000

Data Index: 856446 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.5921. Min Act: -0.0000

Data Index: 330187 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.5910. Min Act: -0.0000

Data Index: 625965 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1278525 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.6243. Min Act: -0.0000

Data Index: 464680 (C4 (Web Text))

Max Activating Token Index: 336