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

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

Neuron 442 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: 3.5494. Min Range: -3.5494

Max Act: 3.5494. Min Act: -0.1700

Data Index: 673392 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4828. Min Act: -0.1700

Data Index: 1203050 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.4858. Min Act: -0.1700

Data Index: 36442 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3760. Min Act: -0.1700

Data Index: 804969 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3350. Min Act: -0.1700

Data Index: 204939 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3388. Min Act: -0.1700

Data Index: 51777 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3487. Min Act: -0.1700

Data Index: 1346821 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3253. Min Act: -0.1700

Data Index: 518336 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3305. Min Act: -0.1700

Data Index: 369351 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.2992. Min Act: -0.1700

Data Index: 185334 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3059. Min Act: -0.1700

Data Index: 732390 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3029. Min Act: -0.1700

Data Index: 157049 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.3036. Min Act: -0.1700

Data Index: 591484 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.2952. Min Act: -0.1700

Data Index: 487287 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.2626. Min Act: -0.1700

Data Index: 187149 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.2691. Min Act: -0.1700

Data Index: 762971 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.2698. Min Act: -0.1700

Data Index: 482617 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.2439. Min Act: -0.1700

Data Index: 308930 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.2753. Min Act: -0.1700

Data Index: 943464 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 3.5494. Min Range: -3.5494

Max Act: 3.2530. Min Act: -0.1700

Data Index: 369493 (C4 (Web Text))

Max Activating Token Index: 550