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

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

Neuron 5139 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: 0.9761. Min Range: -0.9761

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1085993 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.7319. Min Act: -0.0000

Data Index: 312115 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6829. Min Act: -0.0000

Data Index: 268366 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.7023. Min Act: -0.0000

Data Index: 505962 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.7004. Min Act: -0.0000

Data Index: 467314 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1083832 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6391. Min Act: -0.0000

Data Index: 933939 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1007450 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6557. Min Act: -0.0000

Data Index: 604444 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6388. Min Act: -0.0000

Data Index: 66097 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6367. Min Act: -0.0000

Data Index: 984193 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6385. Min Act: -0.0000

Data Index: 404193 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6363. Min Act: -0.0000

Data Index: 678572 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6376. Min Act: -0.0000

Data Index: 707568 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.5931. Min Act: -0.0000

Data Index: 200792 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1221993 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6323. Min Act: -0.0000

Data Index: 290155 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6361. Min Act: -0.0000

Data Index: 503328 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6261. Min Act: -0.0000

Data Index: 297931 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.9761. Min Range: -0.9761

Max Act: 0.6166. Min Act: -0.0000

Data Index: 847382 (C4 (Web Text))

Max Activating Token Index: 749