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

Dataset: Open Web Text

Neuron 33 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: 1.9219. Min Range: -1.9219

Max Act: 1.9219. Min Act: -0.1700

Data Index: 5304010 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.7310. Min Act: -0.1700

Data Index: 5519728 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.5164. Min Act: -0.1700

Data Index: 821196 (Open Web Text)

Max Activating Token Index: 441

Text #3

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.4823. Min Act: -0.1700

Data Index: 6836868 (Open Web Text)

Max Activating Token Index: 426

Text #4

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.4527. Min Act: -0.1700

Data Index: 8436298 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.4455. Min Act: -0.1700

Data Index: 3173231 (Open Web Text)

Max Activating Token Index: 435

Text #6

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.4098. Min Act: -0.1700

Data Index: 6991243 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3936. Min Act: -0.1700

Data Index: 4799921 (Open Web Text)

Max Activating Token Index: 413

Text #8

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.4220. Min Act: -0.1700

Data Index: 4046714 (Open Web Text)

Max Activating Token Index: 410

Text #9

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.4228. Min Act: -0.1700

Data Index: 3527517 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3797. Min Act: -0.1700

Data Index: 8385570 (Open Web Text)

Max Activating Token Index: 414

Text #11

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3938. Min Act: -0.1700

Data Index: 5170190 (Open Web Text)

Max Activating Token Index: 458

Text #12

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3809. Min Act: -0.1700

Data Index: 7585604 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3548. Min Act: -0.1700

Data Index: 6386132 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3522. Min Act: -0.1700

Data Index: 4578270 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3647. Min Act: -0.1700

Data Index: 3759687 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3537. Min Act: -0.1700

Data Index: 8188253 (Open Web Text)

Max Activating Token Index: 447

Text #17

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3686. Min Act: -0.1700

Data Index: 6093416 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3486. Min Act: -0.1700

Data Index: 2656949 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 1.9219. Min Range: -1.9219

Max Act: 1.3409. Min Act: -0.1700

Data Index: 2163461 (Open Web Text)

Max Activating Token Index: 430