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

Dataset: The Pile

Neuron 2927 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1291844 (The Pile)

Max Activating Token Index: 288

Text #1

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1242154 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1267226 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4693. Min Act: -0.0000

Data Index: 348116 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1240687 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1681469 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1863978 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1727689 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1317938 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1566866 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1444975 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1427216 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1376308 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4113. Min Act: -0.0000

Data Index: 439028 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1377228 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.3892. Min Act: -0.0000

Data Index: 835461 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.3769. Min Act: -0.0000

Data Index: 375604 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1329408 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.3798. Min Act: -0.0000

Data Index: 610502 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 0.7129. Min Range: -0.7129

Max Act: 0.3923. Min Act: -0.0000

Data Index: 857593 (The Pile)

Max Activating Token Index: 732