Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9782. Min Act: -0.0001

Data Index: 1113652 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8562. Min Act: -0.0001

Data Index: 415965 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8173. Min Act: -0.0001

Data Index: 1212568 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7494. Min Act: -0.0001

Data Index: 839675 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6968. Min Act: -0.0001

Data Index: 1328094 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7207. Min Act: -0.0001

Data Index: 32134 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6626. Min Act: -0.0001

Data Index: 566979 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7501. Min Act: -0.0001

Data Index: 1223271 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6960. Min Act: -0.0001

Data Index: 741043 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6720. Min Act: -0.0001

Data Index: 490984 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6785. Min Act: -0.0001

Data Index: 811730 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1023746 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1335140 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6393. Min Act: -0.0001

Data Index: 1288548 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6258. Min Act: -0.0001

Data Index: 895459 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6745. Min Act: -0.0001

Data Index: 868888 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6249. Min Act: -0.0001

Data Index: 997872 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6159. Min Act: -0.0001

Data Index: 37959 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6331. Min Act: -0.0001

Data Index: 1327049 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.6057. Min Act: -0.0001

Data Index: 636662 (C4 (Web Text))

Max Activating Token Index: 293