Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4317 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.0438. Min Range: -1.0438

Max Act: 1.0438. Min Act: -0.0001

Data Index: 246278 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.9517. Min Act: -0.0001

Data Index: 1097965 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.9142. Min Act: -0.0001

Data Index: 485064 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.9236. Min Act: -0.0001

Data Index: 940995 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.9022. Min Act: -0.0001

Data Index: 631538 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.9122. Min Act: -0.0001

Data Index: 1305322 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8973. Min Act: -0.0001

Data Index: 1247075 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8959. Min Act: -0.0001

Data Index: 1268075 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.9162. Min Act: -0.0001

Data Index: 1051147 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.9074. Min Act: -0.0001

Data Index: 532031 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8919. Min Act: -0.0002

Data Index: 500453 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8794. Min Act: -0.0001

Data Index: 424328 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8782. Min Act: -0.0001

Data Index: 247625 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8679. Min Act: -0.0001

Data Index: 272221 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8644. Min Act: -0.0001

Data Index: 888606 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8647. Min Act: -0.0001

Data Index: 126260 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8778. Min Act: -0.0001

Data Index: 537451 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8642. Min Act: -0.0001

Data Index: 896063 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8737. Min Act: -0.0001

Data Index: 1098276 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.8659. Min Act: -0.0001

Data Index: 489888 (C4 (Web Text))

Max Activating Token Index: 390