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

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

Neuron 3416 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.2784. Min Act: -0.0000

Data Index: 21318 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.2082. Min Act: 0.0000

Data Index: 282076 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.0719. Min Act: -0.0000

Data Index: 712260 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 3.2784. Min Range: -3.2784

Max Act: 2.3424. Min Act: -0.0000

Data Index: 323746 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 3.2784. Min Range: -3.2784

Max Act: 2.4174. Min Act: -0.0000

Data Index: 966778 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.9359. Min Act: -0.0000

Data Index: 259772 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 3.2784. Min Range: -3.2784

Max Act: 2.2783. Min Act: -0.0000

Data Index: 54746 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.8592. Min Act: -0.0000

Data Index: 55557 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.7503. Min Act: -0.0000

Data Index: 296485 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.8258. Min Act: -0.0000

Data Index: 506974 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.7699. Min Act: -0.0000

Data Index: 981995 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.5614. Min Act: -0.0000

Data Index: 1313644 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.7393. Min Act: -0.0000

Data Index: 46008 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.8313. Min Act: -0.0000

Data Index: 778385 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.6241. Min Act: -0.0000

Data Index: 279181 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.7241. Min Act: -0.0000

Data Index: 691842 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.7191. Min Act: -0.0000

Data Index: 579567 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.7870. Min Act: -0.0000

Data Index: 1172542 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.5804. Min Act: -0.0000

Data Index: 977627 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 3.2784. Min Range: -3.2784

Max Act: 1.7699. Min Act: 0.0000

Data Index: 150762 (C4 (Web Text))

Max Activating Token Index: 812