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

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

Neuron 4904 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.7788. Min Act: -0.0000

Data Index: 35023 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1322537 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.7068. Min Act: -0.0000

Data Index: 476309 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6929. Min Act: -0.0000

Data Index: 102186 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6643. Min Act: -0.0000

Data Index: 831139 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6459. Min Act: -0.0000

Data Index: 385846 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6496. Min Act: -0.0000

Data Index: 238677 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6195. Min Act: -0.0000

Data Index: 340843 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1103900 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1173054 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5821. Min Act: -0.0000

Data Index: 97098 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1266372 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5490. Min Act: -0.0000

Data Index: 42229 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5492. Min Act: -0.0000

Data Index: 666684 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1272088 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5493. Min Act: -0.0000

Data Index: 593175 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5353. Min Act: -0.0000

Data Index: 318342 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5273. Min Act: -0.0000

Data Index: 149473 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5195. Min Act: -0.0000

Data Index: 219563 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5126. Min Act: -0.0000

Data Index: 879899 (C4 (Web Text))

Max Activating Token Index: 806