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

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

Neuron 2232 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1163272 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1001240 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6567. Min Act: -0.0000

Data Index: 675394 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6770. Min Act: -0.0000

Data Index: 168837 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5703. Min Act: -0.0000

Data Index: 311146 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1002067 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5969. Min Act: -0.0000

Data Index: 394652 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1629277 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5156. Min Act: -0.0000

Data Index: 100044 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5874. Min Act: -0.0000

Data Index: 61251 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1029952 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5428. Min Act: -0.0000

Data Index: 626962 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5352. Min Act: -0.0000

Data Index: 736236 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5337. Min Act: 0.0000

Data Index: 1063689 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1203497 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5560. Min Act: -0.0000

Data Index: 789688 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5544. Min Act: -0.0000

Data Index: 44881 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1026296 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5078. Min Act: -0.0000

Data Index: 509480 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.7801. Min Range: -0.7801

Max Act: 0.5055. Min Act: -0.0000

Data Index: 296577 (C4 (Web Text))

Max Activating Token Index: 127