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

Dataset: The Pile

Neuron 4031 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: 0.4134. Min Range: -0.4134

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1264732 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.4134. Min Act: -0.0000

Data Index: 771134 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1935373 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3944. Min Act: -0.0000

Data Index: 952184 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1292013 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3533. Min Act: -0.0000

Data Index: 325380 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3939. Min Act: -0.0000

Data Index: 911656 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3484. Min Act: -0.0000

Data Index: 987616 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1066584 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3729. Min Act: 0.0000

Data Index: 676311 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3446. Min Act: -0.0000

Data Index: 412412 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3440. Min Act: -0.0000

Data Index: 419210 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1956041 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3564. Min Act: -0.0000

Data Index: 901807 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1948116 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3281. Min Act: -0.0000

Data Index: 996173 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1450869 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3516. Min Act: -0.0000

Data Index: 719780 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3295. Min Act: 0.0000

Data Index: 1682050 (The Pile)

Max Activating Token Index: 367

Text #19

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3369. Min Act: -0.0000

Data Index: 510982 (The Pile)

Max Activating Token Index: 711