Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3046 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0646. Min Range: -1.0646

Max Act: 1.0646. Min Act: -0.0000

Data Index: 6305 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.7964. Min Act: -0.0000

Data Index: 151219 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.8176. Min Act: -0.0000

Data Index: 779655 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.7901. Min Act: -0.0000

Data Index: 277167 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.8104. Min Act: -0.0000

Data Index: 105984 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.7333. Min Act: -0.0000

Data Index: 229951 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1200594 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1345147 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6633. Min Act: -0.0000

Data Index: 595922 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1034779 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1322159 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6337. Min Act: -0.0000

Data Index: 417821 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6518. Min Act: -0.0000

Data Index: 389372 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1280694 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1135941 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6304. Min Act: -0.0000

Data Index: 306810 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1343971 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.5984. Min Act: -0.0000

Data Index: 154604 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6102. Min Act: 0.0000

Data Index: 187823 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 1.0646. Min Range: -1.0646

Max Act: 0.6109. Min Act: -0.0000

Data Index: 817031 (C4 (Web Text))

Max Activating Token Index: 162