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

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

Neuron 4695 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: 4.4530. Min Range: -4.4530

Max Act: 4.3792. Min Act: -0.0000

Data Index: 819794 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 4.4530. Min Range: -4.4530

Max Act: 4.3633. Min Act: -0.0000

Data Index: 681347 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 4.4530. Min Range: -4.4530

Max Act: 4.4530. Min Act: -0.0000

Data Index: 336044 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.9245. Min Act: -0.0000

Data Index: 248592 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.8923. Min Act: -0.0000

Data Index: 713332 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.8209. Min Act: -0.0000

Data Index: 756395 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.8115. Min Act: -0.0000

Data Index: 990119 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.9730. Min Act: -0.0000

Data Index: 477850 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 4.4530. Min Range: -4.4530

Max Act: 4.1110. Min Act: -0.0000

Data Index: 954781 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.9201. Min Act: -0.0000

Data Index: 386201 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.7559. Min Act: -0.0000

Data Index: 820391 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.7181. Min Act: -0.0000

Data Index: 981220 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.3183. Min Act: -0.0000

Data Index: 1239767 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.4996. Min Act: -0.0000

Data Index: 951105 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.2817. Min Act: -0.0000

Data Index: 1243433 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.4119. Min Act: -0.0000

Data Index: 81404 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.6754. Min Act: -0.0000

Data Index: 720945 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.3561. Min Act: -0.0000

Data Index: 872367 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.4466. Min Act: -0.0000

Data Index: 456682 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 4.4530. Min Range: -4.4530

Max Act: 3.2513. Min Act: -0.0000

Data Index: 258362 (C4 (Web Text))

Max Activating Token Index: 970