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

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

Neuron 570 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: 2.7589. Min Range: -2.7589

Max Act: 2.7589. Min Act: -0.0000

Data Index: 1009618 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.3530. Min Act: -0.0000

Data Index: 757384 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.4458. Min Act: -0.0000

Data Index: 862689 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.3280. Min Act: -0.0000

Data Index: 372127 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.3362. Min Act: -0.0000

Data Index: 1222844 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.2820. Min Act: -0.0000

Data Index: 484611 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.0259. Min Act: -0.0000

Data Index: 318130 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.1323. Min Act: -0.0000

Data Index: 1130064 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.0047. Min Act: -0.0000

Data Index: 360068 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9761. Min Act: -0.0000

Data Index: 996350 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9649. Min Act: -0.0000

Data Index: 1182385 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9491. Min Act: -0.0000

Data Index: 896128 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9726. Min Act: -0.0000

Data Index: 614672 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9092. Min Act: -0.0000

Data Index: 451581 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9082. Min Act: -0.0000

Data Index: 1344148 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9090. Min Act: -0.0000

Data Index: 484842 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9160. Min Act: -0.0000

Data Index: 793376 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9049. Min Act: -0.0000

Data Index: 152987 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.7890. Min Act: -0.0000

Data Index: 109885 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.7462. Min Act: -0.0000

Data Index: 48263 (C4 (Web Text))

Max Activating Token Index: 92