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

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

Neuron 2720 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0942. Min Range: -1.0942

Max Act: 1.0117. Min Act: -0.0002

Data Index: 711773 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.0942. Min Range: -1.0942

Max Act: 1.0167. Min Act: -0.0002

Data Index: 338502 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9825. Min Act: -0.0002

Data Index: 437476 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9367. Min Act: -0.0002

Data Index: 571526 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9620. Min Act: -0.0002

Data Index: 853644 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9362. Min Act: -0.0002

Data Index: 998578 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9278. Min Act: -0.0002

Data Index: 1281824 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9481. Min Act: -0.0002

Data Index: 333137 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 1.0942. Min Range: -1.0942

Max Act: 1.0942. Min Act: -0.0002

Data Index: 91912 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.0942. Min Range: -1.0942

Max Act: 1.0587. Min Act: -0.0002

Data Index: 879 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.8975. Min Act: -0.0002

Data Index: 470012 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9603. Min Act: -0.0002

Data Index: 354532 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.8985. Min Act: -0.0002

Data Index: 1045783 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9668. Min Act: -0.0002

Data Index: 8163 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.8987. Min Act: -0.0002

Data Index: 1020129 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.8498. Min Act: -0.0002

Data Index: 235469 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.8703. Min Act: -0.0002

Data Index: 372159 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.8687. Min Act: -0.0002

Data Index: 24359 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.9713. Min Act: -0.0002

Data Index: 410063 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.0942. Min Range: -1.0942

Max Act: 0.8844. Min Act: -0.0002

Data Index: 118323 (C4 (Web Text))

Max Activating Token Index: 418