Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4757. Min Act: -0.0001

Data Index: 1086971 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4629. Min Act: -0.0001

Data Index: 484387 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4156. Min Act: -0.0001

Data Index: 1297303 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4416. Min Act: -0.0001

Data Index: 799902 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4315. Min Act: -0.0001

Data Index: 643027 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4287. Min Act: -0.0001

Data Index: 1149083 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4100. Min Act: -0.0001

Data Index: 414958 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3938. Min Act: -0.0001

Data Index: 694210 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.4083. Min Act: -0.0001

Data Index: 1105991 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3983. Min Act: -0.0001

Data Index: 807080 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3556. Min Act: -0.0001

Data Index: 18307 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1254084 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3503. Min Act: -0.0001

Data Index: 823655 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3322. Min Act: -0.0001

Data Index: 617803 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3446. Min Act: -0.0001

Data Index: 385250 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3068. Min Act: -0.0000

Data Index: 463933 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.3049. Min Act: -0.0001

Data Index: 645000 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2811. Min Act: -0.0000

Data Index: 447326 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2933. Min Act: -0.0000

Data Index: 919585 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.4757. Min Range: -0.4757

Max Act: 0.2712. Min Act: -0.0000

Data Index: 141845 (C4 (Web Text))

Max Activating Token Index: 197