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

Dataset: Open Web Text

Neuron 2868 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: 4.3306. Min Range: -4.3306

Max Act: 4.3076. Min Act: -0.1700

Data Index: 7201988 (Open Web Text)

Max Activating Token Index: 656

Text #1

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.3306. Min Act: -0.1700

Data Index: 6917422 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2799. Min Act: -0.1700

Data Index: 1764474 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2826. Min Act: -0.1700

Data Index: 4613331 (Open Web Text)

Max Activating Token Index: 514

Text #4

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2622. Min Act: -0.1700

Data Index: 5275319 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2911. Min Act: -0.1700

Data Index: 6020554 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.3119. Min Act: -0.1700

Data Index: 1303623 (Open Web Text)

Max Activating Token Index: 494

Text #7

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2881. Min Act: -0.1700

Data Index: 4320330 (Open Web Text)

Max Activating Token Index: 605

Text #8

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2386. Min Act: -0.1700

Data Index: 1255040 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2758. Min Act: -0.1700

Data Index: 7535881 (Open Web Text)

Max Activating Token Index: 552

Text #10

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2715. Min Act: -0.1700

Data Index: 2153346 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2197. Min Act: -0.1700

Data Index: 1015302 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2449. Min Act: -0.1700

Data Index: 6247526 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2645. Min Act: -0.1700

Data Index: 3544501 (Open Web Text)

Max Activating Token Index: 486

Text #14

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2408. Min Act: -0.1700

Data Index: 3962488 (Open Web Text)

Max Activating Token Index: 512

Text #15

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2490. Min Act: -0.1700

Data Index: 5710981 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2404. Min Act: -0.1700

Data Index: 5533749 (Open Web Text)

Max Activating Token Index: 489

Text #17

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2443. Min Act: -0.1700

Data Index: 1086582 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2412. Min Act: -0.1700

Data Index: 5084124 (Open Web Text)

Max Activating Token Index: 58

Text #19

Max Range: 4.3306. Min Range: -4.3306

Max Act: 4.2889. Min Act: -0.1700

Data Index: 1613114 (Open Web Text)

Max Activating Token Index: 896