Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4239 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.3225. Min Act: -0.0000

Data Index: 157658 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0731. Min Act: -0.0000

Data Index: 706049 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1129887 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1347111 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0659. Min Act: -0.0000

Data Index: 694893 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0592. Min Act: -0.0000

Data Index: 215658 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1008548 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1059957 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0498. Min Act: -0.0000

Data Index: 218463 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0488. Min Act: -0.0000

Data Index: 947420 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0445. Min Act: -0.0000

Data Index: 165241 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1358709 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0472. Min Act: -0.0000

Data Index: 950540 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0454. Min Act: -0.0000

Data Index: 387719 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0445. Min Act: -0.0000

Data Index: 279510 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0414. Min Act: -0.0000

Data Index: 817909 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1158811 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0361. Min Act: -0.0000

Data Index: 443359 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.0452. Min Act: -0.0000

Data Index: 543183 (C4 (Web Text))

Max Activating Token Index: 811