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

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

Neuron 4648 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.4054. Min Act: -0.0002

Data Index: 475003 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2919. Min Act: -0.0002

Data Index: 813269 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2942. Min Act: -0.0002

Data Index: 1304907 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2924. Min Act: -0.0002

Data Index: 1094075 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3037. Min Act: -0.0002

Data Index: 359463 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2787. Min Act: -0.0002

Data Index: 50329 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2700. Min Act: -0.0002

Data Index: 1351493 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2530. Min Act: -0.0002

Data Index: 879344 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2977. Min Act: -0.0002

Data Index: 1112969 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2621. Min Act: -0.0002

Data Index: 1085723 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2483. Min Act: -0.0002

Data Index: 596140 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2802. Min Act: -0.0002

Data Index: 977273 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2822. Min Act: -0.0002

Data Index: 548073 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2493. Min Act: -0.0002

Data Index: 601089 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2062. Min Act: -0.0002

Data Index: 314388 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1962. Min Act: -0.0002

Data Index: 1330951 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1972. Min Act: -0.0002

Data Index: 1031103 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1910. Min Act: -0.0002

Data Index: 1236970 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1785. Min Act: -0.0002

Data Index: 1004642 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.1782. Min Act: -0.0002

Data Index: 50122 (C4 (Web Text))

Max Activating Token Index: 529