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

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

Neuron 742 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1078540 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.3357. Min Act: -0.0000

Data Index: 947540 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2887. Min Act: -0.0000

Data Index: 137702 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2802. Min Act: -0.0000

Data Index: 11124 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2575. Min Act: -0.0000

Data Index: 233847 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.3030. Min Act: -0.0000

Data Index: 816605 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.3081. Min Act: -0.0000

Data Index: 233444 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2805. Min Act: -0.0000

Data Index: 474256 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2550. Min Act: -0.0000

Data Index: 596591 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.3015. Min Act: -0.0000

Data Index: 85332 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2196. Min Act: -0.0000

Data Index: 330978 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2641. Min Act: -0.0000

Data Index: 553509 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1290202 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1277556 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1152193 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2577. Min Act: -0.0000

Data Index: 232999 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1429437 (Python Code)

Max Activating Token Index: 902

Text #17

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1302259 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2410. Min Act: -0.0000

Data Index: 959718 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.3830. Min Range: -0.3830

Max Act: 0.2534. Min Act: -0.0000

Data Index: 57433 (C4 (Web Text))

Max Activating Token Index: 408