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

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

Neuron 3459 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5547. Min Range: -2.5547

Max Act: 2.3100. Min Act: -0.0000

Data Index: 938641 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 2.5547. Min Range: -2.5547

Max Act: 2.3344. Min Act: -0.0000

Data Index: 618052 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 2.5547. Min Range: -2.5547

Max Act: 2.5547. Min Act: -0.0000

Data Index: 1138691 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 2.5547. Min Range: -2.5547

Max Act: 2.1329. Min Act: -0.0000

Data Index: 466355 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 2.5547. Min Range: -2.5547

Max Act: 2.1230. Min Act: -0.0000

Data Index: 700633 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 2.5547. Min Range: -2.5547

Max Act: 2.0172. Min Act: -0.0000

Data Index: 499428 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.9264. Min Act: -0.0000

Data Index: 721064 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.9721. Min Act: -0.0000

Data Index: 1143934 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 2.5547. Min Range: -2.5547

Max Act: 2.0684. Min Act: -0.0000

Data Index: 1302785 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.7814. Min Act: -0.0000

Data Index: 1005358 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.6545. Min Act: -0.0000

Data Index: 613285 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.7422. Min Act: -0.0000

Data Index: 280202 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.5818. Min Act: -0.0000

Data Index: 479169 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.5697. Min Act: -0.0000

Data Index: 512464 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.5582. Min Act: -0.0000

Data Index: 318130 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.5671. Min Act: -0.0000

Data Index: 617906 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.5387. Min Act: -0.0000

Data Index: 1199499 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.6305. Min Act: -0.0000

Data Index: 1211355 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.3757. Min Act: -0.0000

Data Index: 878532 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 2.5547. Min Range: -2.5547

Max Act: 1.5404. Min Act: -0.0000

Data Index: 907025 (C4 (Web Text))

Max Activating Token Index: 923