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

Dataset: Open Web Text

Neuron 919 in Layer 2

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: 1.8890. Min Range: -1.8890

Max Act: 1.8890. Min Act: -0.1700

Data Index: 6802741 (Open Web Text)

Max Activating Token Index: 473

Text #1

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8657. Min Act: -0.1700

Data Index: 6843622 (Open Web Text)

Max Activating Token Index: 298

Text #2

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8771. Min Act: -0.1700

Data Index: 7949575 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8658. Min Act: -0.1700

Data Index: 6843625 (Open Web Text)

Max Activating Token Index: 152

Text #4

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8495. Min Act: -0.1700

Data Index: 4659580 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8318. Min Act: -0.1700

Data Index: 435657 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8255. Min Act: -0.1700

Data Index: 4594384 (Open Web Text)

Max Activating Token Index: 94

Text #7

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8148. Min Act: -0.1700

Data Index: 296932 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8235. Min Act: -0.1700

Data Index: 8474280 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8202. Min Act: -0.1700

Data Index: 6488389 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8055. Min Act: -0.1700

Data Index: 4322525 (Open Web Text)

Max Activating Token Index: 359

Text #11

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8122. Min Act: -0.1700

Data Index: 4118019 (Open Web Text)

Max Activating Token Index: 213

Text #12

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8171. Min Act: -0.1700

Data Index: 3096083 (Open Web Text)

Max Activating Token Index: 44

Text #13

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8268. Min Act: -0.1697

Data Index: 6366942 (Open Web Text)

Max Activating Token Index: 990

Text #14

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.7973. Min Act: -0.1700

Data Index: 1801007 (Open Web Text)

Max Activating Token Index: 549

Text #15

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8024. Min Act: -0.1700

Data Index: 5775906 (Open Web Text)

Max Activating Token Index: 486

Text #16

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8084. Min Act: -0.1700

Data Index: 6194141 (Open Web Text)

Max Activating Token Index: 679

Text #17

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.7983. Min Act: -0.1700

Data Index: 1824319 (Open Web Text)

Max Activating Token Index: 355

Text #18

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8083. Min Act: -0.1700

Data Index: 1888224 (Open Web Text)

Max Activating Token Index: 531

Text #19

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8220. Min Act: -0.1700

Data Index: 689895 (Open Web Text)

Max Activating Token Index: 1008