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

Dataset: The Pile

Neuron 4917 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: 7.3064. Min Range: -7.3064

Max Act: 7.3064. Min Act: -0.0000

Data Index: 1072789 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.3433. Min Act: -0.0000

Data Index: 241171 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.4558. Min Act: -0.0000

Data Index: 1803634 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.4282. Min Act: -0.0000

Data Index: 454558 (The Pile)

Max Activating Token Index: 943

Text #4

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.4622. Min Act: -0.0000

Data Index: 162662 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.4224. Min Act: -0.0000

Data Index: 1000772 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.4158. Min Act: -0.0000

Data Index: 527161 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.2023. Min Act: -0.0000

Data Index: 490366 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.4032. Min Act: -0.0000

Data Index: 1964812 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.4955. Min Act: -0.0000

Data Index: 1069796 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.0956. Min Act: -0.0000

Data Index: 1429922 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.0537. Min Act: -0.0000

Data Index: 834581 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.2426. Min Act: -0.0000

Data Index: 1477038 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.0379. Min Act: -0.0000

Data Index: 554794 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.0064. Min Act: -0.0000

Data Index: 182751 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 7.3064. Min Range: -7.3064

Max Act: 4.8382. Min Act: -0.0000

Data Index: 409310 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.1054. Min Act: -0.0000

Data Index: 907090 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 7.3064. Min Range: -7.3064

Max Act: 4.5061. Min Act: -0.0000

Data Index: 820950 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.1802. Min Act: -0.0000

Data Index: 297807 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 7.3064. Min Range: -7.3064

Max Act: 5.3772. Min Act: -0.0000

Data Index: 1098287 (The Pile)

Max Activating Token Index: 655