Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1067 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5834. Min Act: -0.0000

Data Index: 908118 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4628. Min Act: -0.0000

Data Index: 509224 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4175. Min Act: -0.0000

Data Index: 494804 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4580. Min Act: -0.0000

Data Index: 820671 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3719. Min Act: -0.0000

Data Index: 824494 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3785. Min Act: -0.0000

Data Index: 117969 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4143. Min Act: -0.0000

Data Index: 959952 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3776. Min Act: -0.0000

Data Index: 107542 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1492907 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1397443 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3786. Min Act: 0.0000

Data Index: 486537 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3994. Min Act: -0.0000

Data Index: 415316 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1399229 (Python Code)

Max Activating Token Index: 136

Text #13

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1065598 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1504973 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1493301 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1037334 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1509859 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1611891 (Python Code)

Max Activating Token Index: 160

Text #19

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1386895 (Python Code)

Max Activating Token Index: 146