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

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

Neuron 5394 in Layer 1

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: 0.8570. Min Range: -0.8570

Max Act: 0.8570. Min Act: -0.0002

Data Index: 789199 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7893. Min Act: -0.0002

Data Index: 828964 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7716. Min Act: -0.0002

Data Index: 19061 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7858. Min Act: -0.0002

Data Index: 378241 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7837. Min Act: -0.0002

Data Index: 486823 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7790. Min Act: -0.0002

Data Index: 300223 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7645. Min Act: -0.0002

Data Index: 3528 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7457. Min Act: -0.0002

Data Index: 1359439 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7455. Min Act: -0.0002

Data Index: 1124791 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7568. Min Act: -0.0002

Data Index: 239569 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7472. Min Act: -0.0002

Data Index: 13588 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7349. Min Act: -0.0002

Data Index: 1091047 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7424. Min Act: -0.0002

Data Index: 699104 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7225. Min Act: -0.0002

Data Index: 195061 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7284. Min Act: -0.0002

Data Index: 544058 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7151. Min Act: -0.0002

Data Index: 661391 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7150. Min Act: -0.0002

Data Index: 600710 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7040. Min Act: -0.0002

Data Index: 1249645 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.7049. Min Act: -0.0002

Data Index: 1223102 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.8570. Min Range: -0.8570

Max Act: 0.6964. Min Act: -0.0002

Data Index: 301308 (C4 (Web Text))

Max Activating Token Index: 35