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

Dataset: The Pile

Neuron 922 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: 1.8040. Min Range: -1.8040

Max Act: 1.8040. Min Act: -0.0000

Data Index: 597541 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1800147 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1175890 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1043698 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1518774 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.2110. Min Act: -0.0000

Data Index: 119518 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1529430 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1444443 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.3503. Min Act: -0.0000

Data Index: 1760013 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.3249. Min Act: -0.0000

Data Index: 296354 (The Pile)

Max Activating Token Index: 126

Text #10

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.2602. Min Act: -0.0000

Data Index: 115297 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1731688 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.2562. Min Act: -0.0000

Data Index: 572428 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.2229. Min Act: 0.0000

Data Index: 1452099 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.1863. Min Act: -0.0000

Data Index: 88457 (The Pile)

Max Activating Token Index: 412

Text #15

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.1108. Min Act: -0.0000

Data Index: 533308 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.1520. Min Act: -0.0000

Data Index: 1377350 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.0768. Min Act: -0.0000

Data Index: 477360 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1171765 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 1.8040. Min Range: -1.8040

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1003730 (The Pile)

Max Activating Token Index: 429