Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 570 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.9730. Min Act: -0.0001

Data Index: 1522861 (Python Code)

Max Activating Token Index: 601

Text #1

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.7672. Min Act: -0.0001

Data Index: 1516855 (Python Code)

Max Activating Token Index: 579

Text #2

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.6650. Min Act: -0.0001

Data Index: 1498429 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.4950. Min Act: -0.0001

Data Index: 1602589 (Python Code)

Max Activating Token Index: 40

Text #4

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.5379. Min Act: -0.0001

Data Index: 1473808 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.6815. Min Act: -0.0001

Data Index: 1393373 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.2475. Min Act: -0.0001

Data Index: 1550310 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.3622. Min Act: -0.0001

Data Index: 1565613 (Python Code)

Max Activating Token Index: 345

Text #8

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.3003. Min Act: -0.0001

Data Index: 1524863 (Python Code)

Max Activating Token Index: 262

Text #9

Max Range: 3.9730. Min Range: -3.9730

Max Act: 2.9982. Min Act: -0.0001

Data Index: 1393717 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.4416. Min Act: -0.0001

Data Index: 1570010 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.2822. Min Act: -0.0001

Data Index: 1385004 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 3.9730. Min Range: -3.9730

Max Act: 2.9958. Min Act: -0.0001

Data Index: 1496738 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.1220. Min Act: -0.0001

Data Index: 1475335 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.1250. Min Act: -0.0001

Data Index: 1429140 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.3962. Min Act: -0.0001

Data Index: 1585182 (Python Code)

Max Activating Token Index: 904

Text #16

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.2538. Min Act: -0.0001

Data Index: 1586581 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.0916. Min Act: -0.0001

Data Index: 1451342 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.0696. Min Act: -0.0001

Data Index: 1427772 (Python Code)

Max Activating Token Index: 278

Text #19

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.0547. Min Act: -0.0001

Data Index: 1546241 (Python Code)

Max Activating Token Index: 647