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

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

Neuron 5261 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6507. Min Range: -4.6507

Max Act: 4.6507. Min Act: -0.0000

Data Index: 564168 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 4.6507. Min Range: -4.6507

Max Act: 4.4398. Min Act: -0.0000

Data Index: 352683 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 4.6507. Min Range: -4.6507

Max Act: 3.9042. Min Act: -0.0000

Data Index: 209843 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 4.6507. Min Range: -4.6507

Max Act: 3.5598. Min Act: -0.0000

Data Index: 1209779 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 4.6507. Min Range: -4.6507

Max Act: 3.0496. Min Act: -0.0000

Data Index: 347977 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.9479. Min Act: -0.0000

Data Index: 1119261 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.6580. Min Act: -0.0000

Data Index: 1422667 (Python Code)

Max Activating Token Index: 632

Text #7

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.2476. Min Act: -0.0000

Data Index: 933820 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.3459. Min Act: -0.0000

Data Index: 1319524 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.1639. Min Act: -0.0000

Data Index: 358931 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.2134. Min Act: -0.0000

Data Index: 660252 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.2900. Min Act: 0.0000

Data Index: 1210722 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.2803. Min Act: -0.0000

Data Index: 1278584 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.2782. Min Act: -0.0000

Data Index: 336953 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.5740. Min Act: -0.0000

Data Index: 1640137 (Python Code)

Max Activating Token Index: 785

Text #15

Max Range: 4.6507. Min Range: -4.6507

Max Act: 1.9597. Min Act: -0.0000

Data Index: 1132089 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.2831. Min Act: -0.0000

Data Index: 1154665 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.0440. Min Act: -0.0000

Data Index: 1619090 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.2544. Min Act: -0.0000

Data Index: 500319 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 4.6507. Min Range: -4.6507

Max Act: 2.1098. Min Act: -0.0000

Data Index: 741175 (C4 (Web Text))

Max Activating Token Index: 72