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

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

Neuron 3672 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4324. Min Act: -0.0000

Data Index: 950008 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3996. Min Act: -0.0000

Data Index: 669539 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4014. Min Act: -0.0000

Data Index: 837306 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3871. Min Act: -0.0000

Data Index: 606833 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3864. Min Act: -0.0000

Data Index: 365229 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1123271 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.4211. Min Act: -0.0000

Data Index: 797634 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1151756 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1177186 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1536395 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1522280 (Python Code)

Max Activating Token Index: 576

Text #11

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3749. Min Act: -0.0000

Data Index: 4288 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1156928 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3457. Min Act: -0.0000

Data Index: 220984 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3540. Min Act: -0.0000

Data Index: 948459 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1081095 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3313. Min Act: -0.0000

Data Index: 661972 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3334. Min Act: -0.0000

Data Index: 698239 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1037875 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.4324. Min Range: -0.4324

Max Act: 0.3203. Min Act: -0.0000

Data Index: 380516 (C4 (Web Text))

Max Activating Token Index: 529