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

Dataset: The Pile

Neuron 672 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.9203. Min Act: -0.0000

Data Index: 1257804 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.8679. Min Act: -0.0000

Data Index: 1575646 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.6308. Min Act: -0.0000

Data Index: 1473398 (The Pile)

Max Activating Token Index: 529

Text #3

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.5823. Min Act: -0.0000

Data Index: 1566889 (The Pile)

Max Activating Token Index: 721

Text #4

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.6861. Min Act: -0.0000

Data Index: 1639740 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.5060. Min Act: -0.0000

Data Index: 364028 (The Pile)

Max Activating Token Index: 39

Text #6

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.6842. Min Act: -0.0000

Data Index: 656477 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.5782. Min Act: -0.0000

Data Index: 1885983 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3926. Min Act: -0.0000

Data Index: 188814 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.1676. Min Act: -0.0000

Data Index: 1828042 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.1143. Min Act: -0.0000

Data Index: 432725 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.6783. Min Act: -0.0000

Data Index: 1889306 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.4649. Min Act: -0.0000

Data Index: 1510019 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.2152. Min Act: -0.0000

Data Index: 1148134 (The Pile)

Max Activating Token Index: 136

Text #14

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.6204. Min Act: -0.0000

Data Index: 72701 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.4023. Min Act: -0.0000

Data Index: 783880 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.3666. Min Act: -0.0000

Data Index: 1204086 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.5651. Min Act: -0.0000

Data Index: 1355099 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.5362. Min Act: -0.0000

Data Index: 1586208 (The Pile)

Max Activating Token Index: 99

Text #19

Max Range: 5.9203. Min Range: -5.9203

Max Act: 5.4961. Min Act: -0.0000

Data Index: 608221 (The Pile)

Max Activating Token Index: 618