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

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

Neuron 515 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: 2.0768. Min Range: -2.0768

Max Act: 2.0768. Min Act: -0.0000

Data Index: 519073 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.9944. Min Act: -0.0000

Data Index: 669839 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.7971. Min Act: -0.0000

Data Index: 589566 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 2.0768. Min Range: -2.0768

Max Act: 2.0003. Min Act: -0.0000

Data Index: 1037766 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.8662. Min Act: -0.0000

Data Index: 989840 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.7407. Min Act: -0.0000

Data Index: 673403 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.7529. Min Act: -0.0000

Data Index: 16903 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5406. Min Act: -0.0000

Data Index: 475482 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.6169. Min Act: -0.0000

Data Index: 602576 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.7008. Min Act: -0.0000

Data Index: 742530 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5797. Min Act: -0.0000

Data Index: 813419 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1059270 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.4661. Min Act: -0.0000

Data Index: 591873 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.6182. Min Act: -0.0000

Data Index: 241475 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5273. Min Act: -0.0000

Data Index: 1272167 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.3450. Min Act: -0.0000

Data Index: 1502677 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.5048. Min Act: -0.0000

Data Index: 508117 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.4508. Min Act: -0.0000

Data Index: 637529 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.4978. Min Act: -0.0000

Data Index: 394935 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 2.0768. Min Range: -2.0768

Max Act: 1.4768. Min Act: -0.0000

Data Index: 843183 (C4 (Web Text))

Max Activating Token Index: 358