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

Dataset: Open Web Text

Neuron 171 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: 2.4828. Min Range: -2.4828

Max Act: 2.4828. Min Act: -0.1700

Data Index: 3247044 (Open Web Text)

Max Activating Token Index: 450

Text #1

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.4623. Min Act: -0.1700

Data Index: 8193699 (Open Web Text)

Max Activating Token Index: 405

Text #2

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.4593. Min Act: -0.1700

Data Index: 7716854 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.4210. Min Act: -0.1700

Data Index: 8723595 (Open Web Text)

Max Activating Token Index: 226

Text #4

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.4133. Min Act: -0.1700

Data Index: 5934945 (Open Web Text)

Max Activating Token Index: 426

Text #5

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3941. Min Act: -0.1700

Data Index: 8287029 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3564. Min Act: -0.1700

Data Index: 7412511 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3484. Min Act: -0.1700

Data Index: 133188 (Open Web Text)

Max Activating Token Index: 808

Text #8

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3405. Min Act: -0.1700

Data Index: 5508721 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3434. Min Act: -0.1700

Data Index: 1672199 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3503. Min Act: -0.1700

Data Index: 2659364 (Open Web Text)

Max Activating Token Index: 257

Text #11

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3399. Min Act: -0.1700

Data Index: 4825403 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3404. Min Act: -0.1700

Data Index: 4782989 (Open Web Text)

Max Activating Token Index: 753

Text #13

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3197. Min Act: -0.1700

Data Index: 2014521 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3274. Min Act: -0.1700

Data Index: 7751604 (Open Web Text)

Max Activating Token Index: 186

Text #15

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3157. Min Act: -0.1700

Data Index: 2659362 (Open Web Text)

Max Activating Token Index: 85

Text #16

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3375. Min Act: -0.1700

Data Index: 5508738 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3349. Min Act: -0.1700

Data Index: 3685390 (Open Web Text)

Max Activating Token Index: 322

Text #18

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3142. Min Act: -0.1700

Data Index: 5110739 (Open Web Text)

Max Activating Token Index: 121

Text #19

Max Range: 2.4828. Min Range: -2.4828

Max Act: 2.3171. Min Act: -0.1700

Data Index: 7076811 (Open Web Text)

Max Activating Token Index: 840