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

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

Neuron 217 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.6056. Min Act: -0.0001

Data Index: 609147 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.6036. Min Act: -0.0001

Data Index: 257118 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5688. Min Act: -0.0001

Data Index: 1066464 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.5013. Min Act: -0.0001

Data Index: 896142 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4642. Min Act: -0.0001

Data Index: 159458 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4723. Min Act: -0.0001

Data Index: 454589 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4662. Min Act: -0.0001

Data Index: 1309334 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1206723 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4646. Min Act: -0.0001

Data Index: 721763 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4773. Min Act: -0.0001

Data Index: 530896 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4644. Min Act: -0.0001

Data Index: 984740 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4511. Min Act: -0.0001

Data Index: 645042 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4718. Min Act: -0.0001

Data Index: 172378 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4396. Min Act: -0.0001

Data Index: 994113 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4587. Min Act: -0.0001

Data Index: 117383 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4114. Min Act: -0.0001

Data Index: 60504 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4204. Min Act: -0.0001

Data Index: 95862 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4330. Min Act: -0.0001

Data Index: 109700 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4314. Min Act: -0.0001

Data Index: 278508 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.6056. Min Range: -0.6056

Max Act: 0.4253. Min Act: -0.0001

Data Index: 649244 (C4 (Web Text))

Max Activating Token Index: 301