Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 391 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.3277. Min Act: -0.0001

Data Index: 911507 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2936. Min Act: -0.0001

Data Index: 334839 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2920. Min Act: -0.0001

Data Index: 873746 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2895. Min Act: -0.0001

Data Index: 106567 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2643. Min Act: -0.0001

Data Index: 557945 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1008977 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2815. Min Act: -0.0001

Data Index: 694644 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2889. Min Act: -0.0001

Data Index: 475267 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2589. Min Act: -0.0001

Data Index: 385549 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2499. Min Act: -0.0001

Data Index: 83769 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2696. Min Act: -0.0001

Data Index: 1077278 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2682. Min Act: -0.0001

Data Index: 119429 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2567. Min Act: -0.0001

Data Index: 566902 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1141107 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2523. Min Act: -0.0001

Data Index: 735165 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2719. Min Act: -0.0001

Data Index: 1219211 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2715. Min Act: -0.0001

Data Index: 237186 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2596. Min Act: -0.0001

Data Index: 39923 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2524. Min Act: -0.0001

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.3277. Min Range: -0.3277

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1096600 (C4 (Web Text))

Max Activating Token Index: 1007