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

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

Neuron 6133 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0573. Min Range: -2.0573

Max Act: 2.0573. Min Act: -0.0000

Data Index: 205347 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 2.0573. Min Range: -2.0573

Max Act: 2.0158. Min Act: -0.0000

Data Index: 713745 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.8813. Min Act: -0.0000

Data Index: 625228 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 2.0573. Min Range: -2.0573

Max Act: 2.0098. Min Act: -0.0000

Data Index: 814331 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.8403. Min Act: -0.0000

Data Index: 1234190 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.7515. Min Act: -0.0000

Data Index: 945881 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.8168. Min Act: -0.0000

Data Index: 215239 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.7065. Min Act: -0.0000

Data Index: 823082 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.7521. Min Act: -0.0000

Data Index: 377458 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.6925. Min Act: -0.0000

Data Index: 163912 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.5495. Min Act: -0.0000

Data Index: 1269574 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.6369. Min Act: -0.0000

Data Index: 1240257 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.5211. Min Act: -0.0000

Data Index: 89555 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1007530 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.6018. Min Act: -0.0000

Data Index: 570262 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1099763 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.4877. Min Act: -0.0000

Data Index: 275357 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.5705. Min Act: -0.0000

Data Index: 342673 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.5545. Min Act: -0.0000

Data Index: 254768 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.0573. Min Range: -2.0573

Max Act: 1.5699. Min Act: -0.0000

Data Index: 1101064 (C4 (Web Text))

Max Activating Token Index: 162