Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 826 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7156. Min Act: 0.0000

Data Index: 958260 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7605. Min Act: -0.0000

Data Index: 344118 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.5388. Min Act: -0.0000

Data Index: 732041 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.3082. Min Act: -0.0000

Data Index: 195798 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.2708. Min Act: -0.0000

Data Index: 242025 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.1207. Min Act: -0.0000

Data Index: 419521 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1315823 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1431534 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1060337 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1332753 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.8002. Min Act: -0.0000

Data Index: 594167 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.9286. Min Act: -0.0000

Data Index: 639053 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.9091. Min Act: -0.0000

Data Index: 423437 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1186182 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.9967. Min Act: 0.0000

Data Index: 1645455 (Python Code)

Max Activating Token Index: 865

Text #15

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1197710 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.8692. Min Act: -0.0000

Data Index: 303992 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1302916 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1047554 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.7605. Min Range: -1.7605

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1368551 (Python Code)

Max Activating Token Index: 180