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

Dataset: Open Web Text

Neuron 754 in Layer 5

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: 3.9347. Min Range: -3.9347

Max Act: 3.9347. Min Act: -0.1700

Data Index: 7662106 (Open Web Text)

Max Activating Token Index: 892

Text #1

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.9073. Min Act: -0.1700

Data Index: 607408 (Open Web Text)

Max Activating Token Index: 754

Text #2

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.8410. Min Act: -0.1700

Data Index: 1823994 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.8001. Min Act: -0.1700

Data Index: 6755514 (Open Web Text)

Max Activating Token Index: 539

Text #4

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7874. Min Act: -0.1700

Data Index: 7297437 (Open Web Text)

Max Activating Token Index: 174

Text #5

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.8224. Min Act: -0.1700

Data Index: 5235402 (Open Web Text)

Max Activating Token Index: 757

Text #6

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.8083. Min Act: -0.1700

Data Index: 4245690 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7946. Min Act: -0.1700

Data Index: 2430616 (Open Web Text)

Max Activating Token Index: 194

Text #8

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7553. Min Act: -0.1700

Data Index: 4312441 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7904. Min Act: -0.1700

Data Index: 5143522 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7638. Min Act: -0.1700

Data Index: 7297435 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7287. Min Act: -0.1700

Data Index: 7297432 (Open Web Text)

Max Activating Token Index: 594

Text #12

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7743. Min Act: -0.1700

Data Index: 1868429 (Open Web Text)

Max Activating Token Index: 505

Text #13

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7471. Min Act: -0.1700

Data Index: 5121229 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7391. Min Act: -0.1700

Data Index: 7740339 (Open Web Text)

Max Activating Token Index: 375

Text #15

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7262. Min Act: -0.1700

Data Index: 7679062 (Open Web Text)

Max Activating Token Index: 357

Text #16

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7585. Min Act: -0.1700

Data Index: 340390 (Open Web Text)

Max Activating Token Index: 218

Text #17

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.6949. Min Act: -0.1700

Data Index: 4361960 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7508. Min Act: -0.1700

Data Index: 4581306 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 3.9347. Min Range: -3.9347

Max Act: 3.7083. Min Act: -0.1700

Data Index: 3163881 (Open Web Text)

Max Activating Token Index: 936