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

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

Neuron 1396 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: 0.4802. Min Range: -0.4802

Max Act: 0.4802. Min Act: -0.0002

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4607. Min Act: -0.0002

Data Index: 970479 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4320. Min Act: -0.0002

Data Index: 535919 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.4311. Min Act: -0.0002

Data Index: 1241181 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3960. Min Act: -0.0002

Data Index: 1203955 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3951. Min Act: -0.0002

Data Index: 1119538 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3752. Min Act: -0.0002

Data Index: 172839 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3745. Min Act: -0.0002

Data Index: 383074 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3769. Min Act: -0.0002

Data Index: 481078 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3734. Min Act: -0.0002

Data Index: 158896 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3656. Min Act: -0.0002

Data Index: 1324222 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3744. Min Act: -0.0002

Data Index: 1074056 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3689. Min Act: -0.0002

Data Index: 1229685 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3635. Min Act: -0.0002

Data Index: 1270832 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3635. Min Act: -0.0002

Data Index: 492316 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3499. Min Act: -0.0002

Data Index: 551468 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3555. Min Act: -0.0002

Data Index: 1173140 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3524. Min Act: -0.0002

Data Index: 661128 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3536. Min Act: -0.0002

Data Index: 1179049 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.4802. Min Range: -0.4802

Max Act: 0.3563. Min Act: -0.0002

Data Index: 1133862 (C4 (Web Text))

Max Activating Token Index: 231