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

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

Neuron 809 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.6085. Min Act: -0.0000

Data Index: 700881 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1244419 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4484. Min Act: -0.0000

Data Index: 78978 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4207. Min Act: -0.0000

Data Index: 754018 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4160. Min Act: -0.0000

Data Index: 621043 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1313562 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3671. Min Act: -0.0000

Data Index: 503301 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4023. Min Act: -0.0000

Data Index: 797308 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4110. Min Act: -0.0000

Data Index: 943209 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3596. Min Act: -0.0000

Data Index: 647770 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3723. Min Act: -0.0000

Data Index: 18083 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3966. Min Act: -0.0001

Data Index: 311971 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3728. Min Act: -0.0001

Data Index: 1276211 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3606. Min Act: -0.0001

Data Index: 559608 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1272178 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3356. Min Act: -0.0000

Data Index: 815356 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3495. Min Act: -0.0001

Data Index: 126550 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3538. Min Act: -0.0001

Data Index: 1314322 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3413. Min Act: -0.0000

Data Index: 972044 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1042920 (C4 (Web Text))

Max Activating Token Index: 956