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

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

Neuron 2694 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0137. Min Range: -2.0137

Max Act: 2.0137. Min Act: -0.0000

Data Index: 1351337 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.8569. Min Act: -0.0000

Data Index: 331056 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.8020. Min Act: -0.0000

Data Index: 1023622 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.7397. Min Act: -0.0000

Data Index: 728522 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.6483. Min Act: -0.0000

Data Index: 1309176 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.4589. Min Act: -0.0000

Data Index: 134723 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.6421. Min Act: -0.0000

Data Index: 868356 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.6039. Min Act: -0.0000

Data Index: 57525 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.5910. Min Act: -0.0000

Data Index: 982082 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.5816. Min Act: -0.0000

Data Index: 1335517 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.5755. Min Act: -0.0000

Data Index: 570081 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.5591. Min Act: -0.0000

Data Index: 355276 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.5405. Min Act: -0.0000

Data Index: 345989 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.6310. Min Act: -0.0000

Data Index: 576310 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.4361. Min Act: -0.0000

Data Index: 317579 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.4246. Min Act: -0.0000

Data Index: 523195 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.4572. Min Act: -0.0000

Data Index: 974787 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.4587. Min Act: -0.0000

Data Index: 175572 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.3622. Min Act: -0.0000

Data Index: 899896 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 2.0137. Min Range: -2.0137

Max Act: 1.4034. Min Act: -0.0000

Data Index: 548450 (C4 (Web Text))

Max Activating Token Index: 145