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

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

Neuron 4596 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: 2.6535. Min Range: -2.6535

Max Act: 2.6535. Min Act: -0.0000

Data Index: 155803 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 2.6535. Min Range: -2.6535

Max Act: 2.5296. Min Act: -0.0000

Data Index: 622655 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 2.6535. Min Range: -2.6535

Max Act: 2.4099. Min Act: -0.0000

Data Index: 656093 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 2.6535. Min Range: -2.6535

Max Act: 2.2185. Min Act: -0.0000

Data Index: 238077 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 2.6535. Min Range: -2.6535

Max Act: 2.1988. Min Act: -0.0000

Data Index: 837256 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 2.6535. Min Range: -2.6535

Max Act: 2.2708. Min Act: -0.0000

Data Index: 495057 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 2.6535. Min Range: -2.6535

Max Act: 2.2505. Min Act: -0.0000

Data Index: 444983 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 2.6535. Min Range: -2.6535

Max Act: 2.1353. Min Act: -0.0000

Data Index: 1206286 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 2.6535. Min Range: -2.6535

Max Act: 2.0326. Min Act: -0.0000

Data Index: 205475 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.9031. Min Act: -0.0000

Data Index: 1074409 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.8747. Min Act: -0.0000

Data Index: 370176 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.7723. Min Act: -0.0000

Data Index: 790698 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.7419. Min Act: -0.0000

Data Index: 896133 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.7477. Min Act: -0.0000

Data Index: 1070322 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.8204. Min Act: -0.0000

Data Index: 364176 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.9073. Min Act: -0.0000

Data Index: 317562 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.7652. Min Act: -0.0000

Data Index: 1328791 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.6445. Min Act: -0.0000

Data Index: 846433 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.7541. Min Act: -0.0000

Data Index: 138559 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 2.6535. Min Range: -2.6535

Max Act: 1.7561. Min Act: -0.0000

Data Index: 950591 (C4 (Web Text))

Max Activating Token Index: 644