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

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

Neuron 580 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0182. Min Act: -0.0000

Data Index: 220658 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.1249. Min Act: -0.0001

Data Index: 1194393 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.4890. Min Act: -0.0000

Data Index: 72066 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.0846. Min Act: -0.0001

Data Index: 1032601 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.2485. Min Act: -0.0001

Data Index: 388938 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.6775. Min Act: -0.0000

Data Index: 128786 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.7776. Min Act: -0.0001

Data Index: 283915 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.9615. Min Act: -0.0000

Data Index: 1179242 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.7832. Min Act: -0.0000

Data Index: 23891 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.7748. Min Act: -0.0000

Data Index: 1335911 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.4092. Min Act: -0.0000

Data Index: 444697 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.6276. Min Act: -0.0001

Data Index: 1037749 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.7523. Min Act: -0.0001

Data Index: 550412 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.4905. Min Act: -0.0001

Data Index: 132745 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.4696. Min Act: -0.0001

Data Index: 809425 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.5636. Min Act: -0.0001

Data Index: 514350 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.3964. Min Act: -0.0001

Data Index: 493684 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.6293. Min Act: -0.0001

Data Index: 1088325 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.6424. Min Act: -0.0001

Data Index: 696340 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 4.1249. Min Range: -4.1249

Max Act: 2.7548. Min Act: -0.0000

Data Index: 864860 (C4 (Web Text))

Max Activating Token Index: 756