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

Dataset: The Pile

Neuron 3690 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.6133. Min Act: -0.0000

Data Index: 1400582 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.4293. Min Act: 0.0000

Data Index: 507322 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.6565. Min Act: -0.0000

Data Index: 1429630 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.8038. Min Act: -0.0000

Data Index: 657498 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.9107. Min Act: -0.0000

Data Index: 368503 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.3671. Min Act: -0.0000

Data Index: 1833385 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.4028. Min Act: -0.0000

Data Index: 152844 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.2867. Min Act: -0.0000

Data Index: 24277 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.8000. Min Act: -0.0000

Data Index: 1129828 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.4581. Min Act: -0.0000

Data Index: 177639 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.4506. Min Act: -0.0000

Data Index: 1017011 (The Pile)

Max Activating Token Index: 616

Text #11

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.4050. Min Act: -0.0000

Data Index: 1415317 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.3566. Min Act: -0.0000

Data Index: 422127 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.4398. Min Act: -0.0000

Data Index: 1339192 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.4619. Min Act: -0.0000

Data Index: 600624 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.2747. Min Act: -0.0000

Data Index: 1340145 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.2699. Min Act: -0.0000

Data Index: 1581293 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.0846. Min Act: -0.0000

Data Index: 340005 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 3.9107. Min Range: -3.9107

Max Act: 3.0786. Min Act: -0.0000

Data Index: 242745 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 3.9107. Min Range: -3.9107

Max Act: 2.8799. Min Act: -0.0000

Data Index: 1951344 (The Pile)

Max Activating Token Index: 39