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

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

Neuron 4754 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.9028. Min Act: -0.0000

Data Index: 752148 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.6880. Min Act: -0.0000

Data Index: 398562 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1305989 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.5785. Min Act: -0.0000

Data Index: 1336790 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.7632. Min Act: -0.0000

Data Index: 19886 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.5413. Min Act: -0.0000

Data Index: 1053091 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.4394. Min Act: -0.0000

Data Index: 719816 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.4864. Min Act: -0.0000

Data Index: 957452 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.4841. Min Act: -0.0000

Data Index: 1019940 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.3974. Min Act: -0.0000

Data Index: 556072 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.4662. Min Act: -0.0000

Data Index: 1312868 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.4455. Min Act: -0.0000

Data Index: 396990 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.3558. Min Act: -0.0000

Data Index: 213172 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1117723 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1134724 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1002073 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.4291. Min Act: -0.0000

Data Index: 407565 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.2711. Min Act: -0.0000

Data Index: 95673 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.3450. Min Act: -0.0000

Data Index: 908887 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.9028. Min Range: -1.9028

Max Act: 1.3457. Min Act: -0.0000

Data Index: 905753 (C4 (Web Text))

Max Activating Token Index: 138