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

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

Neuron 3775 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1286816 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.7043. Min Act: -0.0000

Data Index: 404934 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6503. Min Act: -0.0000

Data Index: 41599 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5689. Min Act: -0.0000

Data Index: 756045 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4865. Min Act: -0.0000

Data Index: 691704 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5196. Min Act: -0.0000

Data Index: 952805 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4694. Min Act: -0.0000

Data Index: 3944 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4776. Min Act: -0.0000

Data Index: 608992 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4560. Min Act: -0.0000

Data Index: 211317 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4500. Min Act: -0.0000

Data Index: 824937 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1309511 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4518. Min Act: 0.0000

Data Index: 1346058 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1344505 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1049064 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4125. Min Act: -0.0000

Data Index: 350923 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1064822 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4831. Min Act: -0.0000

Data Index: 69000 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1287334 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4423. Min Act: -0.0000

Data Index: 84158 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.4137. Min Act: -0.0000

Data Index: 938348 (C4 (Web Text))

Max Activating Token Index: 969