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

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

Neuron 2896 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: 1.6507. Min Range: -1.6507

Max Act: 1.5566. Min Act: -0.0001

Data Index: 812633 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.6507. Min Act: -0.0001

Data Index: 74412 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.5767. Min Act: -0.0001

Data Index: 885657 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.5222. Min Act: -0.0001

Data Index: 457950 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.4980. Min Act: -0.0001

Data Index: 1108477 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.5552. Min Act: -0.0001

Data Index: 753348 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.5872. Min Act: -0.0001

Data Index: 699040 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.4587. Min Act: -0.0001

Data Index: 1250908 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.4975. Min Act: -0.0001

Data Index: 750399 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.5303. Min Act: -0.0001

Data Index: 1336153 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.3823. Min Act: -0.0001

Data Index: 1293441 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.3896. Min Act: -0.0001

Data Index: 1318388 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.5009. Min Act: -0.0001

Data Index: 955149 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.3725. Min Act: -0.0001

Data Index: 276326 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.3571. Min Act: -0.0001

Data Index: 731742 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.4051. Min Act: -0.0001

Data Index: 570439 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.4907. Min Act: -0.0001

Data Index: 713608 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.4547. Min Act: -0.0001

Data Index: 1053028 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.3787. Min Act: -0.0001

Data Index: 599080 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.6507. Min Range: -1.6507

Max Act: 1.3062. Min Act: -0.0001

Data Index: 366860 (C4 (Web Text))

Max Activating Token Index: 293