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

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

Neuron 5196 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: 0.6943. Min Range: -0.6943

Max Act: 0.6943. Min Act: -0.0000

Data Index: 291188 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5980. Min Act: -0.0000

Data Index: 882617 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5288. Min Act: -0.0000

Data Index: 546656 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1121630 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1182892 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1241333 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4736. Min Act: -0.0000

Data Index: 145397 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4376. Min Act: -0.0000

Data Index: 27847 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4415. Min Act: -0.0000

Data Index: 175763 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4334. Min Act: -0.0000

Data Index: 592447 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1190993 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4053. Min Act: -0.0000

Data Index: 579147 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1162834 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.3958. Min Act: -0.0000

Data Index: 209775 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4079. Min Act: -0.0000

Data Index: 640352 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.3890. Min Act: -0.0000

Data Index: 643689 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.3834. Min Act: -0.0000

Data Index: 337506 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.3820. Min Act: -0.0000

Data Index: 309973 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4176. Min Act: -0.0000

Data Index: 830321 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4058. Min Act: -0.0000

Data Index: 407242 (C4 (Web Text))

Max Activating Token Index: 962