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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 195 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1276241 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5526. Min Act: -0.0001

Data Index: 248441 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5030. Min Act: -0.0001

Data Index: 818842 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5027. Min Act: -0.0001

Data Index: 866848 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4929. Min Act: -0.0000

Data Index: 459395 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4862. Min Act: -0.0001

Data Index: 938490 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1327569 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5003. Min Act: -0.0001

Data Index: 92289 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4295. Min Act: -0.0001

Data Index: 433817 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5050. Min Act: -0.0001

Data Index: 114230 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4752. Min Act: -0.0001

Data Index: 1191361 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4889. Min Act: -0.0001

Data Index: 358449 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4367. Min Act: -0.0001

Data Index: 1270757 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4632. Min Act: -0.0001

Data Index: 878101 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4495. Min Act: -0.0000

Data Index: 803877 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4337. Min Act: -0.0001

Data Index: 44566 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4743. Min Act: -0.0001

Data Index: 555030 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4594. Min Act: -0.0001

Data Index: 1350879 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4612. Min Act: -0.0000

Data Index: 605146 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4458. Min Act: -0.0001

Data Index: 840128 (C4 (Web Text))

Max Activating Token Index: 532