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

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

Neuron 4113 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8963. Min Act: -0.0002

Data Index: 457384 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8208. Min Act: -0.0002

Data Index: 1035765 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7562. Min Act: -0.0002

Data Index: 1304165 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7505. Min Act: -0.0002

Data Index: 334429 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7006. Min Act: -0.0002

Data Index: 1150182 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6839. Min Act: -0.0002

Data Index: 49200 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6540. Min Act: -0.0002

Data Index: 1179545 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6736. Min Act: -0.0002

Data Index: 1267283 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6391. Min Act: -0.0002

Data Index: 16525 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6418. Min Act: -0.0002

Data Index: 607199 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6298. Min Act: -0.0002

Data Index: 673216 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5976. Min Act: -0.0002

Data Index: 1253367 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6401. Min Act: -0.0002

Data Index: 256056 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6296. Min Act: -0.0002

Data Index: 755458 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6100. Min Act: -0.0002

Data Index: 348347 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6275. Min Act: -0.0002

Data Index: 1170711 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6070. Min Act: -0.0002

Data Index: 1156541 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5821. Min Act: -0.0002

Data Index: 113296 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6002. Min Act: -0.0002

Data Index: 1265169 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5976. Min Act: -0.0002

Data Index: 907304 (C4 (Web Text))

Max Activating Token Index: 206