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

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

Neuron 2304 in Layer 0

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: 0.5250. Min Range: -0.5250

Max Act: 0.5250. Min Act: -0.0001

Data Index: 421589 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.5089. Min Act: -0.0001

Data Index: 17358 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4970. Min Act: -0.0001

Data Index: 709774 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4685. Min Act: -0.0001

Data Index: 197138 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4552. Min Act: -0.0001

Data Index: 305566 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4610. Min Act: -0.0001

Data Index: 587776 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4651. Min Act: -0.0001

Data Index: 1271155 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4670. Min Act: -0.0001

Data Index: 670619 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4551. Min Act: -0.0001

Data Index: 1293674 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4551. Min Act: -0.0002

Data Index: 879310 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4599. Min Act: -0.0001

Data Index: 730585 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4479. Min Act: -0.0001

Data Index: 277815 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4520. Min Act: -0.0001

Data Index: 864643 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4378. Min Act: -0.0001

Data Index: 442998 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4333. Min Act: -0.0001

Data Index: 673113 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4399. Min Act: -0.0001

Data Index: 1215992 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1338973 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4433. Min Act: -0.0001

Data Index: 483063 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4394. Min Act: -0.0001

Data Index: 837306 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4421. Min Act: -0.0001

Data Index: 57488 (C4 (Web Text))

Max Activating Token Index: 270