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

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

Neuron 352 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1177572 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1618685 (Python Code)

Max Activating Token Index: 192

Text #2

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6305. Min Act: -0.0000

Data Index: 156811 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6216. Min Act: -0.0000

Data Index: 530685 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6547. Min Act: -0.0000

Data Index: 651700 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.6128. Min Act: -0.0000

Data Index: 92695 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5772. Min Act: -0.0000

Data Index: 462245 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1386870 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5862. Min Act: -0.0000

Data Index: 516178 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5239. Min Act: -0.0000

Data Index: 571462 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1399019 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5287. Min Act: -0.0000

Data Index: 726099 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1520966 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5437. Min Act: -0.0000

Data Index: 454240 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1563658 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4987. Min Act: -0.0000

Data Index: 903961 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1046340 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1161740 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.4904. Min Act: -0.0000

Data Index: 430742 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.7069. Min Range: -0.7069

Max Act: 0.5038. Min Act: -0.0000

Data Index: 584694 (C4 (Web Text))

Max Activating Token Index: 51