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

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

Neuron 4655 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: 0.3734. Min Range: -0.3734

Max Act: 0.3734. Min Act: -0.0000

Data Index: 619557 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3382. Min Act: -0.0001

Data Index: 79641 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3612. Min Act: -0.0001

Data Index: 141903 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3416. Min Act: -0.0000

Data Index: 371816 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3474. Min Act: -0.0001

Data Index: 1151561 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3233. Min Act: -0.0001

Data Index: 1126199 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3395. Min Act: -0.0001

Data Index: 1345699 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3519. Min Act: -0.0001

Data Index: 304829 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3177. Min Act: -0.0001

Data Index: 507244 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3158. Min Act: -0.0001

Data Index: 985053 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3260. Min Act: -0.0001

Data Index: 1106815 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1288811 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3140. Min Act: -0.0001

Data Index: 461612 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3002. Min Act: -0.0000

Data Index: 81930 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2803. Min Act: -0.0001

Data Index: 957514 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2958. Min Act: -0.0001

Data Index: 904452 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2862. Min Act: -0.0001

Data Index: 233474 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1083555 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2999. Min Act: -0.0001

Data Index: 8358 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1214650 (C4 (Web Text))

Max Activating Token Index: 131