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

Dataset: Open Web Text

Neuron 799 in Layer 6

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: 3.4565. Min Range: -3.4565

Max Act: 3.4565. Min Act: -0.1700

Data Index: 6757605 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.4357. Min Act: -0.1700

Data Index: 4919717 (Open Web Text)

Max Activating Token Index: 312

Text #2

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.4243. Min Act: -0.1700

Data Index: 2228889 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.4401. Min Act: -0.1700

Data Index: 2228887 (Open Web Text)

Max Activating Token Index: 887

Text #4

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.4138. Min Act: -0.1700

Data Index: 5944862 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.4093. Min Act: -0.1700

Data Index: 2021605 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3931. Min Act: -0.1700

Data Index: 3598830 (Open Web Text)

Max Activating Token Index: 266

Text #7

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.4022. Min Act: -0.1700

Data Index: 2228882 (Open Web Text)

Max Activating Token Index: 189

Text #8

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3926. Min Act: -0.1700

Data Index: 8187809 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3655. Min Act: -0.1700

Data Index: 2434963 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3657. Min Act: -0.1700

Data Index: 6790869 (Open Web Text)

Max Activating Token Index: 99

Text #11

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3698. Min Act: -0.1700

Data Index: 6757604 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3428. Min Act: -0.1700

Data Index: 8187808 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3484. Min Act: -0.1700

Data Index: 7011246 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3466. Min Act: -0.1700

Data Index: 5067625 (Open Web Text)

Max Activating Token Index: 501

Text #15

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3222. Min Act: -0.1700

Data Index: 7131267 (Open Web Text)

Max Activating Token Index: 543

Text #16

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3344. Min Act: -0.1700

Data Index: 4046757 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3348. Min Act: -0.1700

Data Index: 6736615 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.3399. Min Act: -0.1700

Data Index: 5862058 (Open Web Text)

Max Activating Token Index: 161

Text #19

Max Range: 3.4565. Min Range: -3.4565

Max Act: 3.2920. Min Act: -0.1700

Data Index: 610218 (Open Web Text)

Max Activating Token Index: 174