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

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

Neuron 1094 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: 0.9394. Min Range: -0.9394

Max Act: 0.9137. Min Act: -0.0000

Data Index: 890543 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1023736 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7614. Min Act: -0.0000

Data Index: 310467 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.8446. Min Act: -0.0000

Data Index: 117173 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.8279. Min Act: -0.0000

Data Index: 958265 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7971. Min Act: -0.0000

Data Index: 98062 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.8434. Min Act: -0.0000

Data Index: 802496 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.8134. Min Act: -0.0000

Data Index: 486702 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.8159. Min Act: -0.0000

Data Index: 867039 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1074870 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7485. Min Act: -0.0000

Data Index: 980434 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7454. Min Act: -0.0000

Data Index: 383651 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7958. Min Act: -0.0000

Data Index: 928090 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7385. Min Act: -0.0000

Data Index: 156828 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7776. Min Act: -0.0000

Data Index: 276868 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7746. Min Act: -0.0000

Data Index: 66774 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7745. Min Act: -0.0000

Data Index: 741348 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1316231 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7175. Min Act: -0.0000

Data Index: 120394 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.9394. Min Range: -0.9394

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1277093 (C4 (Web Text))

Max Activating Token Index: 112