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

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

Neuron 5058 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2040. Min Range: -2.2040

Max Act: 2.2040. Min Act: -0.0000

Data Index: 106038 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 2.2040. Min Range: -2.2040

Max Act: 2.0522. Min Act: -0.0000

Data Index: 1291322 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.5468. Min Act: -0.0000

Data Index: 517673 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.6913. Min Act: -0.0000

Data Index: 1127163 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1328268 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.3683. Min Act: -0.0000

Data Index: 944143 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.4327. Min Act: -0.0000

Data Index: 654959 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.2721. Min Act: -0.0000

Data Index: 284591 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.4826. Min Act: -0.0000

Data Index: 1294094 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1363478 (Python Code)

Max Activating Token Index: 504

Text #10

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.5109. Min Act: -0.0000

Data Index: 887949 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.4046. Min Act: -0.0000

Data Index: 906704 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1069182 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.4079. Min Act: -0.0000

Data Index: 605732 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.3355. Min Act: -0.0000

Data Index: 503376 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1187577 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.2859. Min Act: -0.0000

Data Index: 440069 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.2540. Min Act: -0.0000

Data Index: 1171729 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1097995 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 2.2040. Min Range: -2.2040

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1323742 (C4 (Web Text))

Max Activating Token Index: 874