Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1957 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.5462. Min Act: -0.1700

Data Index: 901536 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.4782. Min Act: -0.1700

Data Index: 542536 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.4352. Min Act: -0.1700

Data Index: 617730 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3378. Min Act: -0.1700

Data Index: 1199592 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3557. Min Act: -0.1700

Data Index: 204409 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3586. Min Act: -0.1700

Data Index: 940037 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3731. Min Act: -0.1700

Data Index: 367580 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3382. Min Act: -0.1700

Data Index: 971036 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3360. Min Act: -0.1700

Data Index: 737356 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3449. Min Act: -0.1700

Data Index: 583682 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3430. Min Act: -0.1700

Data Index: 311017 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.2727. Min Act: -0.1700

Data Index: 415129 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.2698. Min Act: -0.1700

Data Index: 690391 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.2948. Min Act: -0.1700

Data Index: 756633 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3249. Min Act: -0.1700

Data Index: 317532 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.2527. Min Act: -0.1700

Data Index: 36113 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3371. Min Act: -0.1700

Data Index: 580720 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.3077. Min Act: -0.1700

Data Index: 1359423 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.2290. Min Act: -0.1700

Data Index: 1046872 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 3.5462. Min Range: -3.5462

Max Act: 3.2657. Min Act: -0.1700

Data Index: 753166 (C4 (Web Text))

Max Activating Token Index: 845