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

Dataset: Open Web Text

Neuron 2441 in Layer 4

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: 3.3384. Min Range: -3.3384

Max Act: 3.3384. Min Act: -0.1700

Data Index: 1407574 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.2897. Min Act: -0.1700

Data Index: 8281358 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.2538. Min Act: -0.1700

Data Index: 8261439 (Open Web Text)

Max Activating Token Index: 242

Text #3

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.2350. Min Act: -0.1700

Data Index: 8267951 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.2348. Min Act: -0.1700

Data Index: 8586354 (Open Web Text)

Max Activating Token Index: 958

Text #5

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.2477. Min Act: -0.1700

Data Index: 6845915 (Open Web Text)

Max Activating Token Index: 654

Text #6

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.2030. Min Act: -0.1700

Data Index: 452496 (Open Web Text)

Max Activating Token Index: 143

Text #7

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1982. Min Act: -0.1700

Data Index: 3609526 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1873. Min Act: -0.1700

Data Index: 3351593 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1714. Min Act: -0.1700

Data Index: 6660887 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1767. Min Act: -0.1700

Data Index: 526882 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1502. Min Act: -0.1700

Data Index: 2942614 (Open Web Text)

Max Activating Token Index: 660

Text #12

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1587. Min Act: -0.1700

Data Index: 5192981 (Open Web Text)

Max Activating Token Index: 345

Text #13

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1397. Min Act: -0.1700

Data Index: 3729605 (Open Web Text)

Max Activating Token Index: 406

Text #14

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1357. Min Act: -0.1700

Data Index: 5381234 (Open Web Text)

Max Activating Token Index: 544

Text #15

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1515. Min Act: -0.1700

Data Index: 4983575 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1151. Min Act: -0.1700

Data Index: 8770001 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1077. Min Act: -0.1700

Data Index: 5075942 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1256. Min Act: -0.1700

Data Index: 13717 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 3.3384. Min Range: -3.3384

Max Act: 3.1081. Min Act: -0.1700

Data Index: 7414461 (Open Web Text)

Max Activating Token Index: 585