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

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

Neuron 2991 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: 5.8935. Min Range: -5.8935

Max Act: 5.8935. Min Act: -0.0000

Data Index: 302187 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 5.8935. Min Range: -5.8935

Max Act: 4.5510. Min Act: -0.0000

Data Index: 1041236 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 5.8935. Min Range: -5.8935

Max Act: 4.2316. Min Act: -0.0000

Data Index: 130225 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 5.8935. Min Range: -5.8935

Max Act: 4.0728. Min Act: -0.0000

Data Index: 1126512 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.8389. Min Act: -0.0000

Data Index: 620278 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.8461. Min Act: -0.0000

Data Index: 1219353 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.7485. Min Act: -0.0000

Data Index: 361009 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.7479. Min Act: -0.0000

Data Index: 70097 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.5636. Min Act: -0.0000

Data Index: 284875 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.2692. Min Act: -0.0000

Data Index: 1283261 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.4538. Min Act: -0.0000

Data Index: 1150587 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.3070. Min Act: 0.0000

Data Index: 1038604 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.3544. Min Act: -0.0000

Data Index: 436609 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.2591. Min Act: -0.0000

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.3711. Min Act: 0.0000

Data Index: 552585 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.2631. Min Act: -0.0000

Data Index: 568708 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 5.8935. Min Range: -5.8935

Max Act: 2.9679. Min Act: -0.0000

Data Index: 585054 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.2082. Min Act: -0.0000

Data Index: 1255697 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 5.8935. Min Range: -5.8935

Max Act: 3.0132. Min Act: -0.0000

Data Index: 308326 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 5.8935. Min Range: -5.8935

Max Act: 2.9976. Min Act: -0.0000

Data Index: 268470 (C4 (Web Text))

Max Activating Token Index: 382