Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2239 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1139. Min Range: -1.1139

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1360872 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1541298 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9193. Min Act: -0.0000

Data Index: 665098 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1260087 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7497. Min Act: -0.0000

Data Index: 841492 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1521644 (Python Code)

Max Activating Token Index: 488

Text #6

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1368733 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8346. Min Act: -0.0000

Data Index: 112863 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7951. Min Act: -0.0000

Data Index: 966321 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1507786 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1467947 (Python Code)

Max Activating Token Index: 520

Text #11

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1613189 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1489165 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8559. Min Act: -0.0000

Data Index: 538372 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8175. Min Act: -0.0000

Data Index: 1648564 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1637686 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8126. Min Act: -0.0000

Data Index: 675858 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1435948 (Python Code)

Max Activating Token Index: 651

Text #18

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1415794 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 1.1139. Min Range: -1.1139

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1654224 (Python Code)

Max Activating Token Index: 708