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

Dataset: The Pile

Neuron 312 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.6990. Min Act: -0.0000

Data Index: 604703 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.6638. Min Act: -0.0000

Data Index: 657156 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.4766. Min Act: -0.0000

Data Index: 1943546 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.5765. Min Act: -0.0000

Data Index: 738271 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.3829. Min Act: -0.0000

Data Index: 495587 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.7115. Min Act: -0.0000

Data Index: 676326 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.3193. Min Act: -0.0000

Data Index: 1815231 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.2074. Min Act: -0.0000

Data Index: 1302381 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.5082. Min Act: -0.0000

Data Index: 139632 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.3094. Min Act: -0.0000

Data Index: 1343063 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.6110. Min Act: -0.0000

Data Index: 1021580 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.2866. Min Act: -0.0000

Data Index: 360737 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.4302. Min Act: -0.0000

Data Index: 1691841 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.3560. Min Act: -0.0000

Data Index: 13191 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.1725. Min Act: -0.0000

Data Index: 1939180 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.0055. Min Act: -0.0000

Data Index: 1520412 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.0769. Min Act: -0.0000

Data Index: 1635685 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.1112. Min Act: -0.0000

Data Index: 895834 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.1158. Min Act: -0.0000

Data Index: 1434624 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 5.7115. Min Range: -5.7115

Max Act: 5.0655. Min Act: -0.0000

Data Index: 464874 (The Pile)

Max Activating Token Index: 395