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

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

Neuron 115 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8493. Min Range: -5.8493

Max Act: 5.8493. Min Act: -0.0000

Data Index: 902050 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 5.8493. Min Range: -5.8493

Max Act: 5.6202. Min Act: -0.0000

Data Index: 924720 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 5.8493. Min Range: -5.8493

Max Act: 5.5565. Min Act: -0.0000

Data Index: 113279 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.6374. Min Act: -0.0000

Data Index: 1617772 (Python Code)

Max Activating Token Index: 918

Text #4

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.9080. Min Act: -0.0000

Data Index: 1423289 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.5194. Min Act: -0.0000

Data Index: 1620654 (Python Code)

Max Activating Token Index: 343

Text #6

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.3152. Min Act: -0.0000

Data Index: 1625303 (Python Code)

Max Activating Token Index: 1018

Text #7

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.7560. Min Act: -0.0000

Data Index: 156974 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.5690. Min Act: -0.0000

Data Index: 1557090 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.5152. Min Act: -0.0000

Data Index: 837895 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.4247. Min Act: -0.0000

Data Index: 491348 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.2367. Min Act: -0.0000

Data Index: 1491827 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.9911. Min Act: -0.0000

Data Index: 1380734 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.3474. Min Act: -0.0000

Data Index: 842567 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.4819. Min Act: -0.0000

Data Index: 1335205 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.9776. Min Act: -0.0000

Data Index: 115554 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.3358. Min Act: -0.0000

Data Index: 984664 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 5.8493. Min Range: -5.8493

Max Act: 4.1064. Min Act: -0.0000

Data Index: 576437 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.9276. Min Act: -0.0000

Data Index: 1441966 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 5.8493. Min Range: -5.8493

Max Act: 3.9043. Min Act: -0.0000

Data Index: 1005584 (C4 (Web Text))

Max Activating Token Index: 56