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

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

Neuron 3655 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: 0.9988. Min Range: -0.9988

Max Act: 0.9988. Min Act: -0.0001

Data Index: 328188 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9816. Min Act: -0.0001

Data Index: 592841 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9740. Min Act: -0.0001

Data Index: 1348721 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9754. Min Act: -0.0001

Data Index: 221066 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9781. Min Act: -0.0002

Data Index: 213785 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9491. Min Act: -0.0001

Data Index: 431441 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9302. Min Act: -0.0001

Data Index: 188247 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9259. Min Act: -0.0001

Data Index: 454309 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9319. Min Act: -0.0001

Data Index: 592158 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9163. Min Act: -0.0001

Data Index: 917650 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9430. Min Act: -0.0001

Data Index: 626405 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.8992. Min Act: -0.0001

Data Index: 227085 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9108. Min Act: -0.0001

Data Index: 960354 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9243. Min Act: -0.0001

Data Index: 1034545 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9038. Min Act: -0.0001

Data Index: 667964 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9058. Min Act: -0.0001

Data Index: 516549 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9124. Min Act: -0.0001

Data Index: 715402 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9296. Min Act: -0.0001

Data Index: 682715 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.9079. Min Act: -0.0001

Data Index: 941514 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.9988. Min Range: -0.9988

Max Act: 0.8988. Min Act: -0.0001

Data Index: 1232107 (C4 (Web Text))

Max Activating Token Index: 686