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

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

Neuron 2412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.9055. Min Act: -0.0000

Data Index: 50764 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.6369. Min Act: -0.0000

Data Index: 223772 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.6302. Min Act: -0.0000

Data Index: 1094918 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.5926. Min Act: -0.0000

Data Index: 1215513 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.4925. Min Act: -0.0000

Data Index: 833963 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.5520. Min Act: -0.0000

Data Index: 970913 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.5176. Min Act: -0.0000

Data Index: 779563 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.5020. Min Act: -0.0000

Data Index: 830637 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.4184. Min Act: -0.0000

Data Index: 130000 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.4586. Min Act: -0.0000

Data Index: 162979 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.4323. Min Act: -0.0000

Data Index: 1358220 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.3827. Min Act: -0.0000

Data Index: 242306 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.3826. Min Act: -0.0000

Data Index: 947268 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.3476. Min Act: -0.0000

Data Index: 263637 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.3439. Min Act: -0.0000

Data Index: 1012277 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1277419 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.3273. Min Act: -0.0000

Data Index: 408164 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1297766 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1135596 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 1.9055. Min Range: -1.9055

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1127583 (C4 (Web Text))

Max Activating Token Index: 238