Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1884 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.4051. Min Act: -0.0001

Data Index: 12783 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1633972 (Python Code)

Max Activating Token Index: 494

Text #2

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3476. Min Act: -0.0000

Data Index: 935091 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3434. Min Act: -0.0001

Data Index: 1493926 (Python Code)

Max Activating Token Index: 1002

Text #4

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3179. Min Act: -0.0001

Data Index: 1329099 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3725. Min Act: -0.0001

Data Index: 1044689 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1565279 (Python Code)

Max Activating Token Index: 802

Text #7

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1432350 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3290. Min Act: -0.0001

Data Index: 23272 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1247421 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2903. Min Act: -0.0000

Data Index: 562371 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3103. Min Act: -0.0001

Data Index: 540914 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2865. Min Act: -0.0001

Data Index: 950715 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1222092 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1106673 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2970. Min Act: -0.0001

Data Index: 167922 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2773. Min Act: -0.0001

Data Index: 359451 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1584869 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2910. Min Act: -0.0001

Data Index: 59658 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.4051. Min Range: -0.4051

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1385127 (Python Code)

Max Activating Token Index: 752