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

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

Neuron 4890 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: 2.1277. Min Range: -2.1277

Max Act: 2.1277. Min Act: -0.0000

Data Index: 1182693 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.6786. Min Act: -0.0000

Data Index: 840080 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.7322. Min Act: -0.0000

Data Index: 463565 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.8273. Min Act: -0.0000

Data Index: 978993 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.6432. Min Act: -0.0000

Data Index: 76737 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1310154 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.6047. Min Act: -0.0000

Data Index: 511535 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.6950. Min Act: -0.0000

Data Index: 528847 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.6711. Min Act: -0.0000

Data Index: 569585 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.4677. Min Act: -0.0000

Data Index: 302232 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1142598 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1105506 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.5151. Min Act: -0.0000

Data Index: 699143 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.6045. Min Act: -0.0000

Data Index: 1164969 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.3374. Min Act: -0.0000

Data Index: 78947 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.4854. Min Act: -0.0000

Data Index: 316772 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.5627. Min Act: -0.0000

Data Index: 1217930 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.4764. Min Act: -0.0000

Data Index: 166210 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1053140 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 2.1277. Min Range: -2.1277

Max Act: 1.4654. Min Act: -0.0000

Data Index: 540745 (C4 (Web Text))

Max Activating Token Index: 75