Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3023 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.8745. Min Act: -0.1700

Data Index: 10232 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.8578. Min Act: -0.1700

Data Index: 266818 (Open Web Text)

Max Activating Token Index: 98

Text #2

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.8097. Min Act: -0.1700

Data Index: 6159825 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7781. Min Act: -0.1700

Data Index: 86078 (Open Web Text)

Max Activating Token Index: 553

Text #4

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.8018. Min Act: -0.1700

Data Index: 66233 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7764. Min Act: -0.1700

Data Index: 2844383 (Open Web Text)

Max Activating Token Index: 101

Text #6

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7515. Min Act: -0.1700

Data Index: 8082964 (Open Web Text)

Max Activating Token Index: 344

Text #7

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7862. Min Act: -0.1700

Data Index: 4047904 (Open Web Text)

Max Activating Token Index: 956

Text #8

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7758. Min Act: -0.1700

Data Index: 5730444 (Open Web Text)

Max Activating Token Index: 587

Text #9

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7419. Min Act: -0.1700

Data Index: 8010276 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7468. Min Act: -0.1700

Data Index: 3640536 (Open Web Text)

Max Activating Token Index: 439

Text #11

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7326. Min Act: -0.1700

Data Index: 7296241 (Open Web Text)

Max Activating Token Index: 358

Text #12

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7147. Min Act: -0.1700

Data Index: 7868114 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.7033. Min Act: -0.1700

Data Index: 4813153 (Open Web Text)

Max Activating Token Index: 721

Text #14

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.6869. Min Act: -0.1700

Data Index: 5889843 (Open Web Text)

Max Activating Token Index: 448

Text #15

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.6992. Min Act: -0.1700

Data Index: 2249704 (Open Web Text)

Max Activating Token Index: 921

Text #16

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.6979. Min Act: -0.1700

Data Index: 5717299 (Open Web Text)

Max Activating Token Index: 439

Text #17

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.6624. Min Act: -0.1700

Data Index: 3176839 (Open Web Text)

Max Activating Token Index: 146

Text #18

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.6626. Min Act: -0.1700

Data Index: 4047905 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 3.8745. Min Range: -3.8745

Max Act: 3.6540. Min Act: -0.1700

Data Index: 5532316 (Open Web Text)

Max Activating Token Index: 400