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

Dataset: Open Web Text

Neuron 115 in Layer 5

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: 3.6578. Min Range: -3.6578

Max Act: 3.6578. Min Act: -0.1700

Data Index: 2223679 (Open Web Text)

Max Activating Token Index: 952

Text #1

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.5244. Min Act: -0.1700

Data Index: 6250433 (Open Web Text)

Max Activating Token Index: 865

Text #2

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.4953. Min Act: -0.1700

Data Index: 190018 (Open Web Text)

Max Activating Token Index: 920

Text #3

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.5150. Min Act: -0.1700

Data Index: 4508562 (Open Web Text)

Max Activating Token Index: 449

Text #4

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.5173. Min Act: -0.1700

Data Index: 8612160 (Open Web Text)

Max Activating Token Index: 812

Text #5

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.4866. Min Act: -0.1700

Data Index: 5026949 (Open Web Text)

Max Activating Token Index: 911

Text #6

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.4629. Min Act: -0.1700

Data Index: 7466978 (Open Web Text)

Max Activating Token Index: 252

Text #7

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.4347. Min Act: -0.1700

Data Index: 6947664 (Open Web Text)

Max Activating Token Index: 802

Text #8

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3828. Min Act: -0.1700

Data Index: 2278529 (Open Web Text)

Max Activating Token Index: 228

Text #9

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.4180. Min Act: -0.1700

Data Index: 1001913 (Open Web Text)

Max Activating Token Index: 639

Text #10

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.4126. Min Act: -0.1700

Data Index: 5104496 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3576. Min Act: -0.1700

Data Index: 3581479 (Open Web Text)

Max Activating Token Index: 761

Text #12

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3415. Min Act: -0.1700

Data Index: 7179737 (Open Web Text)

Max Activating Token Index: 98

Text #13

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3224. Min Act: -0.1700

Data Index: 8291626 (Open Web Text)

Max Activating Token Index: 235

Text #14

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3187. Min Act: -0.1700

Data Index: 2675807 (Open Web Text)

Max Activating Token Index: 301

Text #15

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3411. Min Act: -0.1700

Data Index: 7679297 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3207. Min Act: -0.1700

Data Index: 3346812 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3253. Min Act: -0.1700

Data Index: 5415693 (Open Web Text)

Max Activating Token Index: 859

Text #18

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.3099. Min Act: -0.1700

Data Index: 3203808 (Open Web Text)

Max Activating Token Index: 228

Text #19

Max Range: 3.6578. Min Range: -3.6578

Max Act: 3.2819. Min Act: -0.1700

Data Index: 4586711 (Open Web Text)

Max Activating Token Index: 610