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

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

Neuron 3694 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.7040. Min Act: -0.0001

Data Index: 1124271 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.4500. Min Act: -0.0000

Data Index: 949598 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.4689. Min Act: -0.0001

Data Index: 400184 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.3684. Min Act: -0.0001

Data Index: 1549659 (Python Code)

Max Activating Token Index: 208

Text #4

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.4009. Min Act: -0.0000

Data Index: 280835 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.3976. Min Act: -0.0001

Data Index: 312260 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.3467. Min Act: -0.0001

Data Index: 1346259 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.3670. Min Act: -0.0000

Data Index: 424331 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1290036 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.3278. Min Act: -0.0000

Data Index: 1059564 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.2804. Min Act: -0.0000

Data Index: 587556 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.3660. Min Act: -0.0001

Data Index: 374857 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.2776. Min Act: -0.0000

Data Index: 437966 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.3560. Min Act: -0.0001

Data Index: 1538648 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.1948. Min Act: -0.0001

Data Index: 355101 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.3535. Min Act: -0.0001

Data Index: 388367 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.2697. Min Act: -0.0001

Data Index: 1206325 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1219011 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.2568. Min Act: -0.0000

Data Index: 701400 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 1.7040. Min Range: -1.7040

Max Act: 1.2574. Min Act: -0.0001

Data Index: 923448 (C4 (Web Text))

Max Activating Token Index: 175