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

Dataset: Open Web Text

Neuron 2619 in Layer 3

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: 3.4216. Min Range: -3.4216

Max Act: 3.4216. Min Act: -0.1700

Data Index: 4886626 (Open Web Text)

Max Activating Token Index: 794

Text #1

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3807. Min Act: -0.1700

Data Index: 4927182 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3317. Min Act: -0.1700

Data Index: 6718975 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3705. Min Act: -0.1700

Data Index: 4154371 (Open Web Text)

Max Activating Token Index: 999

Text #4

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3314. Min Act: -0.1700

Data Index: 1405504 (Open Web Text)

Max Activating Token Index: 425

Text #5

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3411. Min Act: -0.1700

Data Index: 3653324 (Open Web Text)

Max Activating Token Index: 881

Text #6

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3199. Min Act: -0.1700

Data Index: 760624 (Open Web Text)

Max Activating Token Index: 776

Text #7

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3147. Min Act: -0.1700

Data Index: 7612246 (Open Web Text)

Max Activating Token Index: 806

Text #8

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2993. Min Act: -0.1700

Data Index: 988429 (Open Web Text)

Max Activating Token Index: 93

Text #9

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3163. Min Act: -0.1700

Data Index: 415403 (Open Web Text)

Max Activating Token Index: 390

Text #10

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2926. Min Act: -0.1700

Data Index: 2675316 (Open Web Text)

Max Activating Token Index: 243

Text #11

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.3176. Min Act: -0.1700

Data Index: 478626 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2878. Min Act: -0.1700

Data Index: 7875236 (Open Web Text)

Max Activating Token Index: 891

Text #13

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2977. Min Act: -0.1700

Data Index: 2272722 (Open Web Text)

Max Activating Token Index: 242

Text #14

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2815. Min Act: -0.1700

Data Index: 876653 (Open Web Text)

Max Activating Token Index: 241

Text #15

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2479. Min Act: -0.1700

Data Index: 6106668 (Open Web Text)

Max Activating Token Index: 886

Text #16

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2978. Min Act: -0.1700

Data Index: 5689926 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2671. Min Act: -0.1700

Data Index: 7087181 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2674. Min Act: -0.1700

Data Index: 4916057 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 3.4216. Min Range: -3.4216

Max Act: 3.2331. Min Act: -0.1700

Data Index: 2185999 (Open Web Text)

Max Activating Token Index: 453