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

Dataset: Open Web Text

Neuron 2921 in Layer 1

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: 1.8324. Min Range: -1.8324

Max Act: 1.8324. Min Act: -0.1699

Data Index: 5705598 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.8038. Min Act: -0.1699

Data Index: 1853665 (Open Web Text)

Max Activating Token Index: 318

Text #2

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7591. Min Act: -0.1700

Data Index: 2403516 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7590. Min Act: -0.1700

Data Index: 7680177 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7604. Min Act: -0.1699

Data Index: 3259728 (Open Web Text)

Max Activating Token Index: 274

Text #5

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7318. Min Act: -0.1581

Data Index: 225363 (Open Web Text)

Max Activating Token Index: 521

Text #6

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7258. Min Act: -0.1700

Data Index: 8672269 (Open Web Text)

Max Activating Token Index: 109

Text #7

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7167. Min Act: -0.1700

Data Index: 6791978 (Open Web Text)

Max Activating Token Index: 72

Text #8

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7220. Min Act: -0.1698

Data Index: 187419 (Open Web Text)

Max Activating Token Index: 319

Text #9

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7253. Min Act: -0.1700

Data Index: 2184458 (Open Web Text)

Max Activating Token Index: 336

Text #10

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.7086. Min Act: -0.1700

Data Index: 8383465 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6978. Min Act: -0.1700

Data Index: 4818248 (Open Web Text)

Max Activating Token Index: 641

Text #12

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6982. Min Act: -0.1696

Data Index: 2043640 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6976. Min Act: -0.1700

Data Index: 3657330 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6932. Min Act: -0.1698

Data Index: 3163842 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6934. Min Act: -0.1700

Data Index: 585742 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6824. Min Act: -0.1700

Data Index: 2661579 (Open Web Text)

Max Activating Token Index: 664

Text #17

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6875. Min Act: -0.1699

Data Index: 3278296 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6845. Min Act: -0.1698

Data Index: 6864245 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 1.8324. Min Range: -1.8324

Max Act: 1.6852. Min Act: -0.1700

Data Index: 7181156 (Open Web Text)

Max Activating Token Index: 645