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

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

Neuron 1205 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4590. Min Act: -0.0000

Data Index: 252821 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4321. Min Act: -0.0000

Data Index: 532669 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4357. Min Act: -0.0000

Data Index: 750222 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3581. Min Act: 0.0000

Data Index: 257827 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3159. Min Act: -0.0000

Data Index: 676725 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1100393 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3294. Min Act: -0.0000

Data Index: 816874 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3295. Min Act: -0.0000

Data Index: 391834 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3267. Min Act: -0.0000

Data Index: 881449 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3053. Min Act: -0.0000

Data Index: 707960 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3355. Min Act: -0.0000

Data Index: 118597 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3106. Min Act: -0.0000

Data Index: 605755 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2949. Min Act: -0.0000

Data Index: 596797 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1228457 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1095441 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2958. Min Act: -0.0000

Data Index: 33792 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3147. Min Act: -0.0000

Data Index: 437236 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3070. Min Act: -0.0000

Data Index: 377172 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2968. Min Act: -0.0000

Data Index: 493040 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2944. Min Act: -0.0000

Data Index: 992479 (C4 (Web Text))

Max Activating Token Index: 492