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

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

Neuron 3119 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: 3.1835. Min Range: -3.1835

Max Act: 3.1835. Min Act: -0.0000

Data Index: 953588 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 3.1835. Min Range: -3.1835

Max Act: 2.5536. Min Act: -0.0000

Data Index: 1107398 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.1835. Min Range: -3.1835

Max Act: 2.3846. Min Act: -0.0000

Data Index: 669462 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.8228. Min Act: -0.0000

Data Index: 893097 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.4675. Min Act: -0.0000

Data Index: 194391 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.6228. Min Act: -0.0000

Data Index: 160318 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.5600. Min Act: -0.0000

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1476478 (Python Code)

Max Activating Token Index: 433

Text #8

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.4731. Min Act: -0.0000

Data Index: 94197 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.4483. Min Act: -0.0000

Data Index: 1077408 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.4781. Min Act: -0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.3658. Min Act: -0.0000

Data Index: 683357 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.3236. Min Act: -0.0000

Data Index: 626596 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.3986. Min Act: -0.0000

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.2818. Min Act: -0.0000

Data Index: 1216243 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.3229. Min Act: -0.0000

Data Index: 489434 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.2407. Min Act: -0.0000

Data Index: 879377 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.2394. Min Act: -0.0000

Data Index: 411255 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1344032 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.1835. Min Range: -3.1835

Max Act: 1.1451. Min Act: -0.0000

Data Index: 429270 (C4 (Web Text))

Max Activating Token Index: 510