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

Dataset: Open Web Text

Neuron 383 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: 3.4067. Min Range: -3.4067

Max Act: 3.4067. Min Act: -0.1700

Data Index: 2013313 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3880. Min Act: -0.1700

Data Index: 4924290 (Open Web Text)

Max Activating Token Index: 586

Text #2

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3819. Min Act: -0.1700

Data Index: 5913054 (Open Web Text)

Max Activating Token Index: 465

Text #3

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3584. Min Act: -0.1700

Data Index: 824609 (Open Web Text)

Max Activating Token Index: 246

Text #4

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3358. Min Act: -0.1700

Data Index: 6746312 (Open Web Text)

Max Activating Token Index: 293

Text #5

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2997. Min Act: -0.1700

Data Index: 6013956 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2753. Min Act: -0.1700

Data Index: 4881940 (Open Web Text)

Max Activating Token Index: 726

Text #7

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2561. Min Act: -0.1700

Data Index: 5537095 (Open Web Text)

Max Activating Token Index: 379

Text #8

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2621. Min Act: -0.1700

Data Index: 2233193 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2588. Min Act: -0.1700

Data Index: 5913051 (Open Web Text)

Max Activating Token Index: 350

Text #10

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2718. Min Act: -0.1700

Data Index: 1415892 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2582. Min Act: -0.1700

Data Index: 499916 (Open Web Text)

Max Activating Token Index: 773

Text #12

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2400. Min Act: -0.1700

Data Index: 8789813 (Open Web Text)

Max Activating Token Index: 391

Text #13

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2257. Min Act: -0.1700

Data Index: 6696102 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2199. Min Act: -0.1700

Data Index: 8551839 (Open Web Text)

Max Activating Token Index: 229

Text #15

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2148. Min Act: -0.1700

Data Index: 1139838 (Open Web Text)

Max Activating Token Index: 61

Text #16

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2075. Min Act: -0.1700

Data Index: 589443 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2186. Min Act: -0.1700

Data Index: 7636209 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2128. Min Act: -0.1700

Data Index: 5617768 (Open Web Text)

Max Activating Token Index: 82

Text #19

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.2052. Min Act: -0.1700

Data Index: 4924289 (Open Web Text)

Max Activating Token Index: 357