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

Dataset: The Pile

Neuron 2654 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4219. Min Range: -3.4219

Max Act: 3.2892. Min Act: -0.0000

Data Index: 1749795 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 3.4219. Min Range: -3.4219

Max Act: 3.1287. Min Act: -0.0000

Data Index: 876856 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 3.4219. Min Range: -3.4219

Max Act: 3.4219. Min Act: -0.0000

Data Index: 1858964 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 3.4219. Min Range: -3.4219

Max Act: 3.1864. Min Act: -0.0000

Data Index: 776899 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.6586. Min Act: -0.0000

Data Index: 917710 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.6548. Min Act: -0.0000

Data Index: 1077181 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.7915. Min Act: -0.0000

Data Index: 41811 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.9303. Min Act: -0.0000

Data Index: 617089 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.6315. Min Act: -0.0000

Data Index: 201614 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 3.4219. Min Range: -3.4219

Max Act: 1.9875. Min Act: -0.0000

Data Index: 1232472 (The Pile)

Max Activating Token Index: 964

Text #10

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.6174. Min Act: -0.0000

Data Index: 1930626 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.6059. Min Act: -0.0000

Data Index: 1645898 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.5504. Min Act: -0.0000

Data Index: 294904 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.7875. Min Act: -0.0000

Data Index: 1000740 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.6672. Min Act: -0.0000

Data Index: 1915231 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.5208. Min Act: -0.0000

Data Index: 1501602 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.8025. Min Act: -0.0000

Data Index: 416887 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.7474. Min Act: -0.0000

Data Index: 523279 (The Pile)

Max Activating Token Index: 915

Text #18

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.7719. Min Act: -0.0000

Data Index: 250138 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 3.4219. Min Range: -3.4219

Max Act: 2.4660. Min Act: -0.0000

Data Index: 556252 (The Pile)

Max Activating Token Index: 931