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

Dataset: The Pile

Neuron 1221 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7580. Min Act: -0.0000

Data Index: 728174 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7097. Min Act: -0.0000

Data Index: 556707 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1260388 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6321. Min Act: -0.0000

Data Index: 163186 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6909. Min Act: -0.0000

Data Index: 982819 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6151. Min Act: -0.0000

Data Index: 727149 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1153903 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1754858 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1834230 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1569544 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1882246 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1799224 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1555236 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1174499 (The Pile)

Max Activating Token Index: 383

Text #14

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1183559 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1710043 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1267108 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1691953 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1524441 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5528. Min Act: -0.0000

Data Index: 516330 (The Pile)

Max Activating Token Index: 915