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

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

Neuron 5951 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: 1.4019. Min Range: -1.4019

Max Act: 1.4019. Min Act: -0.0002

Data Index: 465258 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3663. Min Act: -0.0002

Data Index: 1276447 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3880. Min Act: -0.0002

Data Index: 895042 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3650. Min Act: -0.0002

Data Index: 275596 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3886. Min Act: -0.0002

Data Index: 520957 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3677. Min Act: -0.0002

Data Index: 784251 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3354. Min Act: -0.0002

Data Index: 342843 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3320. Min Act: -0.0002

Data Index: 132535 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3547. Min Act: -0.0003

Data Index: 35989 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3425. Min Act: -0.0002

Data Index: 263978 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3389. Min Act: -0.0003

Data Index: 664086 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.2985. Min Act: -0.0002

Data Index: 1106620 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3391. Min Act: -0.0002

Data Index: 362969 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.2908. Min Act: -0.0002

Data Index: 1338289 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3045. Min Act: -0.0002

Data Index: 1007567 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.2899. Min Act: -0.0002

Data Index: 575957 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3001. Min Act: -0.0002

Data Index: 648399 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.3026. Min Act: -0.0002

Data Index: 837237 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.2927. Min Act: -0.0002

Data Index: 298857 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 1.4019. Min Range: -1.4019

Max Act: 1.2800. Min Act: -0.0002

Data Index: 900317 (C4 (Web Text))

Max Activating Token Index: 568