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

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

Neuron 1675 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: 1.8195. Min Range: -1.8195

Max Act: 1.8195. Min Act: -0.0002

Data Index: 315565 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.7135. Min Act: -0.0002

Data Index: 121114 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.5581. Min Act: -0.0002

Data Index: 1017136 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.5635. Min Act: -0.0002

Data Index: 272402 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4932. Min Act: -0.0002

Data Index: 1244138 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4704. Min Act: -0.0002

Data Index: 1176144 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4806. Min Act: -0.0003

Data Index: 551507 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.5083. Min Act: -0.0002

Data Index: 715847 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4394. Min Act: -0.0002

Data Index: 7749 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4520. Min Act: -0.0002

Data Index: 118520 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4470. Min Act: -0.0002

Data Index: 219695 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4486. Min Act: -0.0002

Data Index: 202139 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4407. Min Act: -0.0002

Data Index: 1193270 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4389. Min Act: -0.0002

Data Index: 842584 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4759. Min Act: -0.0002

Data Index: 316652 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4016. Min Act: -0.0002

Data Index: 994542 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4017. Min Act: -0.0002

Data Index: 17762 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4299. Min Act: -0.0002

Data Index: 51262 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.3935. Min Act: -0.0002

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.8195. Min Range: -1.8195

Max Act: 1.4103. Min Act: -0.0002

Data Index: 186636 (C4 (Web Text))

Max Activating Token Index: 134