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

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

Neuron 3023 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.3084. Min Range: -9.3084

Max Act: 9.3084. Min Act: -0.0000

Data Index: 146682 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 9.3084. Min Range: -9.3084

Max Act: 8.6065. Min Act: -0.0000

Data Index: 1007257 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 9.3084. Min Range: -9.3084

Max Act: 8.2717. Min Act: -0.0000

Data Index: 1060859 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 9.3084. Min Range: -9.3084

Max Act: 8.5993. Min Act: -0.0000

Data Index: 1083882 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 9.3084. Min Range: -9.3084

Max Act: 8.2225. Min Act: -0.0000

Data Index: 466178 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 9.3084. Min Range: -9.3084

Max Act: 8.3411. Min Act: -0.0000

Data Index: 1067645 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 9.3084. Min Range: -9.3084

Max Act: 8.0870. Min Act: -0.0000

Data Index: 25997 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 9.3084. Min Range: -9.3084

Max Act: 8.0471. Min Act: -0.0000

Data Index: 231396 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 9.3084. Min Range: -9.3084

Max Act: 8.0227. Min Act: -0.0000

Data Index: 962140 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.8708. Min Act: -0.0000

Data Index: 1302518 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.6120. Min Act: -0.0000

Data Index: 770464 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.5632. Min Act: -0.0000

Data Index: 21540 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.3925. Min Act: -0.0000

Data Index: 890543 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.6878. Min Act: -0.0000

Data Index: 1253629 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.2647. Min Act: -0.0000

Data Index: 886393 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.3672. Min Act: -0.0000

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 9.3084. Min Range: -9.3084

Max Act: 6.9635. Min Act: -0.0000

Data Index: 1344935 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.5230. Min Act: -0.0000

Data Index: 991239 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.3297. Min Act: -0.0000

Data Index: 5534 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 9.3084. Min Range: -9.3084

Max Act: 7.0941. Min Act: -0.0000

Data Index: 376872 (C4 (Web Text))

Max Activating Token Index: 895