Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2232 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.5146. Min Act: -0.0004

Data Index: 239184 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.5155. Min Act: -0.0004

Data Index: 56791 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4578. Min Act: -0.0004

Data Index: 1173423 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4704. Min Act: -0.0004

Data Index: 274701 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4196. Min Act: -0.0004

Data Index: 70351 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4430. Min Act: -0.0004

Data Index: 1092417 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4241. Min Act: -0.0004

Data Index: 569664 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4854. Min Act: -0.0004

Data Index: 1104604 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4517. Min Act: -0.0004

Data Index: 907342 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4174. Min Act: -0.0004

Data Index: 874271 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4733. Min Act: -0.0004

Data Index: 719858 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4137. Min Act: -0.0004

Data Index: 531253 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4131. Min Act: -0.0004

Data Index: 1246254 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4526. Min Act: -0.0004

Data Index: 1236559 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4335. Min Act: -0.0004

Data Index: 289794 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4188. Min Act: -0.0004

Data Index: 29807 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4439. Min Act: -0.0004

Data Index: 1257722 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4888. Min Act: -0.0004

Data Index: 239912 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4239. Min Act: -0.0004

Data Index: 1040225 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.5155. Min Range: -0.5155

Max Act: 0.4246. Min Act: -0.0004

Data Index: 887682 (C4 (Web Text))

Max Activating Token Index: 80