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

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

Neuron 342 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9373. Min Act: -0.0001

Data Index: 441521 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 1.0080. Min Range: -1.0080

Max Act: 1.0080. Min Act: -0.0001

Data Index: 782597 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9457. Min Act: -0.0001

Data Index: 290485 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9149. Min Act: -0.0001

Data Index: 283824 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8767. Min Act: -0.0001

Data Index: 604294 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9257. Min Act: -0.0001

Data Index: 1169358 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9223. Min Act: -0.0001

Data Index: 374521 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8829. Min Act: -0.0001

Data Index: 1010202 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9094. Min Act: -0.0001

Data Index: 1032476 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9070. Min Act: -0.0001

Data Index: 358216 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8972. Min Act: -0.0001

Data Index: 392934 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8904. Min Act: -0.0001

Data Index: 1272389 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.9131. Min Act: -0.0001

Data Index: 477011 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8405. Min Act: -0.0001

Data Index: 1146699 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8232. Min Act: -0.0001

Data Index: 857681 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8456. Min Act: -0.0001

Data Index: 871990 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8407. Min Act: -0.0001

Data Index: 413015 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8104. Min Act: -0.0001

Data Index: 591925 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.8502. Min Act: -0.0001

Data Index: 1088010 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.0080. Min Range: -1.0080

Max Act: 0.7482. Min Act: -0.0001

Data Index: 770440 (C4 (Web Text))

Max Activating Token Index: 492