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

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

Neuron 1177 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: 4.1871. Min Range: -4.1871

Max Act: 4.0471. Min Act: -0.0001

Data Index: 1302780 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.9403. Min Act: -0.0001

Data Index: 1250587 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 4.1871. Min Range: -4.1871

Max Act: 4.1871. Min Act: -0.0001

Data Index: 1178698 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.9096. Min Act: -0.0001

Data Index: 659830 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.3065. Min Act: -0.0001

Data Index: 206045 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.5657. Min Act: -0.0001

Data Index: 845149 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.1841. Min Act: -0.0001

Data Index: 72544 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.6502. Min Act: -0.0001

Data Index: 969211 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.3336. Min Act: -0.0001

Data Index: 916469 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.4267. Min Act: -0.0001

Data Index: 1263413 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.2807. Min Act: -0.0001

Data Index: 786051 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.7340. Min Act: -0.0001

Data Index: 549304 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.3017. Min Act: -0.0001

Data Index: 1302964 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.3971. Min Act: -0.0001

Data Index: 231998 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.5057. Min Act: -0.0001

Data Index: 811629 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.5533. Min Act: -0.0001

Data Index: 866600 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.2330. Min Act: -0.0001

Data Index: 167220 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.3440. Min Act: -0.0001

Data Index: 789838 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.2234. Min Act: -0.0001

Data Index: 1034212 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 4.1871. Min Range: -4.1871

Max Act: 3.1794. Min Act: -0.0001

Data Index: 347976 (C4 (Web Text))

Max Activating Token Index: 446