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

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

Neuron 791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.9092. Min Act: -0.0001

Data Index: 869540 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.8937. Min Act: -0.0001

Data Index: 1034649 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.8916. Min Act: -0.0001

Data Index: 256916 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7704. Min Act: -0.0001

Data Index: 131119 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7571. Min Act: -0.0001

Data Index: 979510 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7333. Min Act: -0.0001

Data Index: 1283296 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7302. Min Act: -0.0001

Data Index: 346964 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7276. Min Act: -0.0001

Data Index: 1112102 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7037. Min Act: -0.0001

Data Index: 1253935 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7449. Min Act: -0.0001

Data Index: 195179 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7403. Min Act: -0.0001

Data Index: 44149 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7337. Min Act: -0.0001

Data Index: 48549 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.6858. Min Act: -0.0001

Data Index: 493990 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7324. Min Act: -0.0001

Data Index: 737150 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7523. Min Act: -0.0001

Data Index: 735461 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7774. Min Act: -0.0001

Data Index: 1358088 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7521. Min Act: -0.0001

Data Index: 518115 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7446. Min Act: -0.0001

Data Index: 309609 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7410. Min Act: -0.0001

Data Index: 414364 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.7231. Min Act: -0.0001

Data Index: 559166 (C4 (Web Text))

Max Activating Token Index: 44