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

Dataset: The Pile

Neuron 2664 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: 0.5374. Min Range: -0.5374

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1272175 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4939. Min Act: -0.0000

Data Index: 35980 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4650. Min Act: -0.0000

Data Index: 881632 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1379850 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1089273 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3902. Min Act: -0.0000

Data Index: 197186 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1715824 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4290. Min Act: -0.0000

Data Index: 707783 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1752491 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.4127. Min Act: -0.0000

Data Index: 448235 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3773. Min Act: -0.0000

Data Index: 366731 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3397. Min Act: -0.0000

Data Index: 387694 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1731450 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1020650 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1298642 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3479. Min Act: -0.0000

Data Index: 552932 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1504030 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3169. Min Act: -0.0000

Data Index: 417920 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.2874. Min Act: -0.0000

Data Index: 61717 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 0.5374. Min Range: -0.5374

Max Act: 0.3103. Min Act: -0.0000

Data Index: 683498 (The Pile)

Max Activating Token Index: 364