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

Dataset: The Pile

Neuron 4402 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1209981 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.4007. Min Act: -0.0000

Data Index: 191949 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1535851 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3615. Min Act: -0.0000

Data Index: 1102215 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3269. Min Act: -0.0000

Data Index: 348436 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1919625 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3731. Min Act: -0.0000

Data Index: 362215 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3202. Min Act: -0.0000

Data Index: 1592762 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3524. Min Act: -0.0000

Data Index: 1135367 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1244579 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1093881 (The Pile)

Max Activating Token Index: 170

Text #11

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1206276 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2580. Min Act: -0.0000

Data Index: 1441690 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2997. Min Act: -0.0000

Data Index: 606197 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2579. Min Act: -0.0000

Data Index: 588491 (The Pile)

Max Activating Token Index: 864

Text #15

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1329389 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1385689 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.2838. Min Act: -0.0000

Data Index: 1538057 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3229. Min Act: -0.0000

Data Index: 1311400 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 1.4255. Min Range: -1.4255

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1660221 (The Pile)

Max Activating Token Index: 996