Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2819 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1517. Min Range: -1.1517

Max Act: 1.1517. Min Act: -0.0002

Data Index: 1110576 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9903. Min Act: -0.0002

Data Index: 488211 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9780. Min Act: -0.0002

Data Index: 822482 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9293. Min Act: -0.0002

Data Index: 966350 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9441. Min Act: -0.0002

Data Index: 796800 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9105. Min Act: -0.0001

Data Index: 989252 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9077. Min Act: -0.0002

Data Index: 561211 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9341. Min Act: -0.0002

Data Index: 969943 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1099807 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8895. Min Act: -0.0002

Data Index: 1160263 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8836. Min Act: -0.0002

Data Index: 78243 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8288. Min Act: -0.0002

Data Index: 651098 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.9138. Min Act: -0.0002

Data Index: 1025650 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8776. Min Act: -0.0001

Data Index: 334062 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.7669. Min Act: -0.0001

Data Index: 918946 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8470. Min Act: -0.0002

Data Index: 1258075 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.7919. Min Act: -0.0002

Data Index: 888729 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8172. Min Act: -0.0002

Data Index: 682065 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.7848. Min Act: -0.0002

Data Index: 399781 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 1.1517. Min Range: -1.1517

Max Act: 0.8565. Min Act: -0.0002

Data Index: 320083 (C4 (Web Text))

Max Activating Token Index: 509