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

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

Neuron 710 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.5208. Min Act: -0.0000

Data Index: 1079534 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.3824. Min Act: -0.0000

Data Index: 1215384 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.3223. Min Act: -0.0000

Data Index: 327691 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.1831. Min Act: -0.0000

Data Index: 606249 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.3028. Min Act: -0.0000

Data Index: 1282904 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.0973. Min Act: -0.0000

Data Index: 782343 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.1921. Min Act: -0.0000

Data Index: 527746 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.0748. Min Act: -0.0000

Data Index: 930864 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.9302. Min Act: -0.0000

Data Index: 807394 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.0082. Min Act: -0.0000

Data Index: 1556052 (Python Code)

Max Activating Token Index: 449

Text #10

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.9004. Min Act: -0.0000

Data Index: 104935 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 2.5208. Min Range: -2.5208

Max Act: 2.0241. Min Act: -0.0000

Data Index: 1145341 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.9010. Min Act: -0.0000

Data Index: 359698 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.7549. Min Act: -0.0000

Data Index: 1326680 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.7120. Min Act: -0.0000

Data Index: 1135903 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.9164. Min Act: -0.0000

Data Index: 1344151 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.7998. Min Act: -0.0000

Data Index: 412955 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.7667. Min Act: -0.0000

Data Index: 546749 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.8747. Min Act: -0.0000

Data Index: 800506 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 2.5208. Min Range: -2.5208

Max Act: 1.7669. Min Act: -0.0000

Data Index: 787070 (C4 (Web Text))

Max Activating Token Index: 833