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

Dataset: The Pile

Neuron 3627 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4073. Min Range: -1.4073

Max Act: 1.4073. Min Act: -0.0000

Data Index: 1787485 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 1.4073. Min Range: -1.4073

Max Act: 1.0356. Min Act: -0.0000

Data Index: 407206 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.8831. Min Act: -0.0000

Data Index: 571345 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.8398. Min Act: -0.0000

Data Index: 630492 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.9034. Min Act: -0.0000

Data Index: 551496 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.8432. Min Act: 0.0000

Data Index: 225643 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.8442. Min Act: -0.0000

Data Index: 310748 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1668598 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1218981 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.7601. Min Act: 0.0000

Data Index: 704504 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1919103 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.6873. Min Act: -0.0000

Data Index: 177306 (The Pile)

Max Activating Token Index: 272

Text #12

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1027133 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1327652 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.6747. Min Act: 0.0000

Data Index: 811164 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1141466 (The Pile)

Max Activating Token Index: 599

Text #16

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.7523. Min Act: -0.0000

Data Index: 662880 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1814365 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1643896 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 1.4073. Min Range: -1.4073

Max Act: 0.6908. Min Act: 0.0000

Data Index: 1391410 (The Pile)

Max Activating Token Index: 153