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

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

Neuron 5655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5272. Min Range: -3.5272

Max Act: 3.3734. Min Act: -0.0001

Data Index: 56432 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 3.5272. Min Range: -3.5272

Max Act: 3.5272. Min Act: -0.0001

Data Index: 934920 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 3.5272. Min Range: -3.5272

Max Act: 3.2141. Min Act: -0.0001

Data Index: 876085 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 3.5272. Min Range: -3.5272

Max Act: 3.5171. Min Act: -0.0001

Data Index: 470740 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 3.5272. Min Range: -3.5272

Max Act: 3.0730. Min Act: -0.0001

Data Index: 972163 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 3.5272. Min Range: -3.5272

Max Act: 3.1646. Min Act: -0.0001

Data Index: 30349 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.5272. Min Range: -3.5272

Max Act: 3.1312. Min Act: -0.0001

Data Index: 789076 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 3.5272. Min Range: -3.5272

Max Act: 3.0953. Min Act: -0.0001

Data Index: 679296 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.8707. Min Act: -0.0001

Data Index: 181957 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.7482. Min Act: -0.0001

Data Index: 1352833 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.6229. Min Act: -0.0001

Data Index: 927766 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.8450. Min Act: -0.0001

Data Index: 1257851 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.5712. Min Act: -0.0001

Data Index: 887756 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.9574. Min Act: -0.0001

Data Index: 1164792 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.9595. Min Act: -0.0001

Data Index: 1036582 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.9489. Min Act: -0.0001

Data Index: 781315 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.8251. Min Act: -0.0001

Data Index: 1052279 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.5725. Min Act: -0.0001

Data Index: 671357 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.8905. Min Act: -0.0001

Data Index: 947617 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 3.5272. Min Range: -3.5272

Max Act: 2.7800. Min Act: -0.0001

Data Index: 1216888 (C4 (Web Text))

Max Activating Token Index: 98