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

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

Neuron 3150 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3250. Min Range: -1.3250

Max Act: 1.3250. Min Act: -0.0001

Data Index: 779399 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.7004. Min Act: -0.0001

Data Index: 1271651 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.8404. Min Act: -0.0001

Data Index: 1006034 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.6826. Min Act: -0.0001

Data Index: 1295225 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1295773 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.6525. Min Act: -0.0001

Data Index: 617562 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1122835 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.6371. Min Act: -0.0001

Data Index: 1086273 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.7995. Min Act: -0.0001

Data Index: 88323 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.6133. Min Act: -0.0001

Data Index: 64948 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5364. Min Act: -0.0001

Data Index: 727994 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5897. Min Act: -0.0001

Data Index: 1045431 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5787. Min Act: -0.0001

Data Index: 1194627 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5928. Min Act: -0.0001

Data Index: 69639 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5680. Min Act: -0.0001

Data Index: 280949 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5499. Min Act: -0.0001

Data Index: 880696 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5399. Min Act: -0.0001

Data Index: 478878 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5310. Min Act: -0.0001

Data Index: 294397 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.6343. Min Act: -0.0001

Data Index: 533587 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.3250. Min Range: -1.3250

Max Act: 0.5086. Min Act: -0.0001

Data Index: 120514 (C4 (Web Text))

Max Activating Token Index: 381