Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 218 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3529. Min Act: -0.0003

Data Index: 343065 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2850. Min Act: -0.0003

Data Index: 569693 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2742. Min Act: -0.0003

Data Index: 659607 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2660. Min Act: -0.0003

Data Index: 971455 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2463. Min Act: -0.0002

Data Index: 948513 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2461. Min Act: -0.0003

Data Index: 1082604 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2417. Min Act: -0.0003

Data Index: 216047 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2271. Min Act: -0.0003

Data Index: 592717 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2262. Min Act: -0.0003

Data Index: 286379 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2154. Min Act: -0.0002

Data Index: 28962 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2220. Min Act: -0.0003

Data Index: 748363 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2125. Min Act: -0.0003

Data Index: 277128 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2163. Min Act: -0.0003

Data Index: 132504 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2159. Min Act: -0.0003

Data Index: 820098 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2160. Min Act: -0.0003

Data Index: 443082 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2151. Min Act: -0.0002

Data Index: 883922 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2139. Min Act: -0.0003

Data Index: 643767 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2120. Min Act: -0.0002

Data Index: 1322792 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2086. Min Act: -0.0003

Data Index: 1005802 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2080. Min Act: -0.0003

Data Index: 1310614 (C4 (Web Text))

Max Activating Token Index: 272