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

Dataset: Open Web Text

Neuron 1297 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: 3.6017. Min Range: -3.6017

Max Act: 3.6017. Min Act: -0.1700

Data Index: 1507000 (Open Web Text)

Max Activating Token Index: 939

Text #1

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5735. Min Act: -0.1700

Data Index: 1473681 (Open Web Text)

Max Activating Token Index: 368

Text #2

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5737. Min Act: -0.1700

Data Index: 3616043 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5538. Min Act: -0.1700

Data Index: 3453671 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5345. Min Act: -0.1700

Data Index: 4053578 (Open Web Text)

Max Activating Token Index: 267

Text #5

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5583. Min Act: -0.1700

Data Index: 6047820 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5469. Min Act: -0.1700

Data Index: 6873862 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5065. Min Act: -0.1700

Data Index: 2451518 (Open Web Text)

Max Activating Token Index: 641

Text #8

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.4999. Min Act: -0.1700

Data Index: 7426052 (Open Web Text)

Max Activating Token Index: 608

Text #9

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5467. Min Act: -0.1700

Data Index: 7056728 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5261. Min Act: -0.1700

Data Index: 6921621 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5017. Min Act: -0.1700

Data Index: 1605499 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5258. Min Act: -0.1700

Data Index: 6562276 (Open Web Text)

Max Activating Token Index: 317

Text #13

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5179. Min Act: -0.1700

Data Index: 5977409 (Open Web Text)

Max Activating Token Index: 764

Text #14

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5267. Min Act: -0.1700

Data Index: 4892418 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5221. Min Act: -0.1700

Data Index: 4312415 (Open Web Text)

Max Activating Token Index: 857

Text #16

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5224. Min Act: -0.1700

Data Index: 829358 (Open Web Text)

Max Activating Token Index: 323

Text #17

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.5192. Min Act: -0.1700

Data Index: 3918630 (Open Web Text)

Max Activating Token Index: 204

Text #18

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.4904. Min Act: -0.1700

Data Index: 3329285 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.6017. Min Range: -3.6017

Max Act: 3.4820. Min Act: -0.1700

Data Index: 463120 (Open Web Text)

Max Activating Token Index: 515