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

Dataset: Open Web Text

Neuron 1127 in Layer 0

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: 1.4934. Min Range: -1.4934

Max Act: 1.4934. Min Act: -0.0730

Data Index: 6334746 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4452. Min Act: -0.1551

Data Index: 2393100 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4369. Min Act: -0.0964

Data Index: 2113886 (Open Web Text)

Max Activating Token Index: 697

Text #3

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4349. Min Act: -0.1416

Data Index: 2924201 (Open Web Text)

Max Activating Token Index: 619

Text #4

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4382. Min Act: -0.1143

Data Index: 3036135 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4267. Min Act: -0.0627

Data Index: 1052925 (Open Web Text)

Max Activating Token Index: 321

Text #6

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4298. Min Act: -0.1174

Data Index: 3600494 (Open Web Text)

Max Activating Token Index: 817

Text #7

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4260. Min Act: -0.1340

Data Index: 7008054 (Open Web Text)

Max Activating Token Index: 668

Text #8

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4223. Min Act: -0.1199

Data Index: 2278843 (Open Web Text)

Max Activating Token Index: 939

Text #9

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4209. Min Act: -0.1159

Data Index: 6021318 (Open Web Text)

Max Activating Token Index: 443

Text #10

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4194. Min Act: -0.0647

Data Index: 4810817 (Open Web Text)

Max Activating Token Index: 335

Text #11

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4256. Min Act: -0.1484

Data Index: 3964215 (Open Web Text)

Max Activating Token Index: 704

Text #12

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4210. Min Act: -0.1282

Data Index: 3654525 (Open Web Text)

Max Activating Token Index: 567

Text #13

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4258. Min Act: -0.1640

Data Index: 3369449 (Open Web Text)

Max Activating Token Index: 591

Text #14

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4143. Min Act: -0.1585

Data Index: 7721368 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4187. Min Act: -0.0630

Data Index: 8786911 (Open Web Text)

Max Activating Token Index: 583

Text #16

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4134. Min Act: -0.1070

Data Index: 632583 (Open Web Text)

Max Activating Token Index: 791

Text #17

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4115. Min Act: -0.1028

Data Index: 1078084 (Open Web Text)

Max Activating Token Index: 534

Text #18

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4008. Min Act: -0.1027

Data Index: 557349 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 1.4934. Min Range: -1.4934

Max Act: 1.4029. Min Act: -0.0741

Data Index: 1020587 (Open Web Text)

Max Activating Token Index: 668