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

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

Neuron 4312 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1657. Min Range: -6.1657

Max Act: 6.1657. Min Act: -0.0000

Data Index: 81584 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 6.1657. Min Range: -6.1657

Max Act: 5.4277. Min Act: -0.0000

Data Index: 177565 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 6.1657. Min Range: -6.1657

Max Act: 4.6785. Min Act: -0.0000

Data Index: 269758 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 6.1657. Min Range: -6.1657

Max Act: 4.5819. Min Act: -0.0000

Data Index: 870446 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 6.1657. Min Range: -6.1657

Max Act: 4.6747. Min Act: -0.0000

Data Index: 265324 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 6.1657. Min Range: -6.1657

Max Act: 4.4069. Min Act: -0.0000

Data Index: 1222044 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 6.1657. Min Range: -6.1657

Max Act: 4.5558. Min Act: -0.0000

Data Index: 760212 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 6.1657. Min Range: -6.1657

Max Act: 4.0388. Min Act: -0.0000

Data Index: 275452 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 6.1657. Min Range: -6.1657

Max Act: 4.3030. Min Act: -0.0000

Data Index: 695484 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.9721. Min Act: -0.0000

Data Index: 391945 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.9290. Min Act: -0.0000

Data Index: 799826 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.4546. Min Act: -0.0000

Data Index: 211297 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.8987. Min Act: -0.0000

Data Index: 263373 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.5496. Min Act: -0.0000

Data Index: 293822 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.6747. Min Act: -0.0000

Data Index: 1044699 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.6761. Min Act: -0.0000

Data Index: 1072068 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 6.1657. Min Range: -6.1657

Max Act: 4.0137. Min Act: -0.0000

Data Index: 1319729 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.6025. Min Act: -0.0000

Data Index: 276022 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.5340. Min Act: -0.0000

Data Index: 803149 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 6.1657. Min Range: -6.1657

Max Act: 3.6091. Min Act: -0.0000

Data Index: 327042 (C4 (Web Text))

Max Activating Token Index: 778