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

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

Neuron 33 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3185. Min Range: -1.3185

Max Act: 1.3185. Min Act: -0.0000

Data Index: 949369 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.3185. Min Range: -1.3185

Max Act: 1.1918. Min Act: -0.0000

Data Index: 736790 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 1.3185. Min Range: -1.3185

Max Act: 1.1863. Min Act: -0.0000

Data Index: 666467 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.3185. Min Range: -1.3185

Max Act: 1.0489. Min Act: -0.0000

Data Index: 400205 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.9924. Min Act: -0.0000

Data Index: 478303 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 1.3185. Min Range: -1.3185

Max Act: 1.0138. Min Act: -0.0000

Data Index: 251219 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.8823. Min Act: -0.0000

Data Index: 250283 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.7241. Min Act: -0.0000

Data Index: 675739 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.6433. Min Act: -0.0000

Data Index: 387483 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.6716. Min Act: 0.0000

Data Index: 1181787 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.6166. Min Act: -0.0000

Data Index: 22308 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.6318. Min Act: -0.0000

Data Index: 260199 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.6319. Min Act: -0.0000

Data Index: 166705 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.5844. Min Act: -0.0000

Data Index: 40732 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.5631. Min Act: -0.0000

Data Index: 498098 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1344557 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.5337. Min Act: -0.0000

Data Index: 224965 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.5657. Min Act: -0.0000

Data Index: 916216 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1213107 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.3185. Min Range: -1.3185

Max Act: 0.5361. Min Act: -0.0000

Data Index: 650675 (C4 (Web Text))

Max Activating Token Index: 476