Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4970 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3183. Min Act: -0.0001

Data Index: 75510 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3275. Min Act: -0.0000

Data Index: 860920 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3321. Min Act: -0.0001

Data Index: 444606 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3631. Min Act: -0.0001

Data Index: 1163325 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3235. Min Act: -0.0001

Data Index: 1346681 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1178414 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3411. Min Act: -0.0001

Data Index: 634600 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3086. Min Act: -0.0001

Data Index: 790432 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3158. Min Act: -0.0001

Data Index: 1171952 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2970. Min Act: -0.0001

Data Index: 321754 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2989. Min Act: -0.0001

Data Index: 1349436 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2978. Min Act: -0.0001

Data Index: 583007 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2924. Min Act: -0.0001

Data Index: 164623 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2926. Min Act: -0.0001

Data Index: 1352264 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2945. Min Act: -0.0000

Data Index: 284183 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1256528 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.3014. Min Act: -0.0001

Data Index: 1321305 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2918. Min Act: -0.0001

Data Index: 884684 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2975. Min Act: -0.0001

Data Index: 643473 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.3631. Min Range: -0.3631

Max Act: 0.2861. Min Act: -0.0001

Data Index: 440073 (C4 (Web Text))

Max Activating Token Index: 131