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

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

Neuron 3892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7803. Min Range: -4.7803

Max Act: 4.7803. Min Act: -0.0000

Data Index: 916578 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 4.7803. Min Range: -4.7803

Max Act: 3.8797. Min Act: -0.0000

Data Index: 85925 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 4.7803. Min Range: -4.7803

Max Act: 3.7105. Min Act: -0.0000

Data Index: 193597 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 4.7803. Min Range: -4.7803

Max Act: 3.3904. Min Act: -0.0000

Data Index: 797558 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 4.7803. Min Range: -4.7803

Max Act: 3.6298. Min Act: -0.0000

Data Index: 259202 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.9477. Min Act: -0.0000

Data Index: 504488 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 4.7803. Min Range: -4.7803

Max Act: 3.2301. Min Act: -0.0000

Data Index: 939849 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 4.7803. Min Range: -4.7803

Max Act: 3.3097. Min Act: -0.0000

Data Index: 432484 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.8680. Min Act: -0.0000

Data Index: 1160042 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.8617. Min Act: -0.0000

Data Index: 227165 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.9748. Min Act: -0.0000

Data Index: 326809 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 4.7803. Min Range: -4.7803

Max Act: 3.0525. Min Act: -0.0000

Data Index: 515462 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.7341. Min Act: -0.0000

Data Index: 499487 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 4.7803. Min Range: -4.7803

Max Act: 3.1193. Min Act: -0.0000

Data Index: 602698 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.7432. Min Act: -0.0000

Data Index: 346886 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.7256. Min Act: -0.0000

Data Index: 870498 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.6372. Min Act: -0.0000

Data Index: 1027720 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.8424. Min Act: -0.0000

Data Index: 1144609 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.7144. Min Act: -0.0000

Data Index: 352380 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 4.7803. Min Range: -4.7803

Max Act: 2.7593. Min Act: -0.0000

Data Index: 961591 (C4 (Web Text))

Max Activating Token Index: 250