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

Dataset: Open Web Text

Neuron 2361 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: 3.5300. Min Range: -3.5300

Max Act: 3.5300. Min Act: -0.1700

Data Index: 3570142 (Open Web Text)

Max Activating Token Index: 385

Text #1

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.5267. Min Act: -0.1700

Data Index: 5117228 (Open Web Text)

Max Activating Token Index: 842

Text #2

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.5040. Min Act: -0.1700

Data Index: 6426530 (Open Web Text)

Max Activating Token Index: 557

Text #3

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.5074. Min Act: -0.1700

Data Index: 4200999 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4805. Min Act: -0.1700

Data Index: 5836404 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.5034. Min Act: -0.1700

Data Index: 4622777 (Open Web Text)

Max Activating Token Index: 342

Text #6

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.5005. Min Act: -0.1700

Data Index: 6535797 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4757. Min Act: -0.1700

Data Index: 4933087 (Open Web Text)

Max Activating Token Index: 979

Text #8

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4552. Min Act: -0.1700

Data Index: 7135801 (Open Web Text)

Max Activating Token Index: 942

Text #9

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4737. Min Act: -0.1700

Data Index: 7647913 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4550. Min Act: -0.1700

Data Index: 1697006 (Open Web Text)

Max Activating Token Index: 52

Text #11

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4599. Min Act: -0.1700

Data Index: 2659445 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4571. Min Act: -0.1700

Data Index: 1058525 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4458. Min Act: -0.1700

Data Index: 3140911 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4464. Min Act: -0.1700

Data Index: 4566990 (Open Web Text)

Max Activating Token Index: 249

Text #15

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4452. Min Act: -0.1700

Data Index: 3778611 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4382. Min Act: -0.1700

Data Index: 4101703 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4612. Min Act: -0.1700

Data Index: 6318902 (Open Web Text)

Max Activating Token Index: 587

Text #18

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4665. Min Act: -0.1700

Data Index: 781174 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 3.5300. Min Range: -3.5300

Max Act: 3.4572. Min Act: -0.1700

Data Index: 4433257 (Open Web Text)

Max Activating Token Index: 943