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

Dataset: Open Web Text

Neuron 882 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: 3.9276. Min Range: -3.9276

Max Act: 3.9276. Min Act: -0.1700

Data Index: 3288460 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.8968. Min Act: -0.1700

Data Index: 4399348 (Open Web Text)

Max Activating Token Index: 483

Text #2

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.8681. Min Act: -0.1700

Data Index: 2212249 (Open Web Text)

Max Activating Token Index: 705

Text #3

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.8538. Min Act: -0.1700

Data Index: 8165300 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.8423. Min Act: -0.1700

Data Index: 3152780 (Open Web Text)

Max Activating Token Index: 972

Text #5

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.8204. Min Act: -0.1700

Data Index: 7114124 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7818. Min Act: -0.1700

Data Index: 7679207 (Open Web Text)

Max Activating Token Index: 321

Text #7

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7635. Min Act: -0.1700

Data Index: 3029360 (Open Web Text)

Max Activating Token Index: 300

Text #8

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7572. Min Act: -0.1700

Data Index: 4347297 (Open Web Text)

Max Activating Token Index: 321

Text #9

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7821. Min Act: -0.1700

Data Index: 1253280 (Open Web Text)

Max Activating Token Index: 361

Text #10

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7710. Min Act: -0.1700

Data Index: 7006426 (Open Web Text)

Max Activating Token Index: 558

Text #11

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7611. Min Act: -0.1700

Data Index: 6285745 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7395. Min Act: -0.1700

Data Index: 869276 (Open Web Text)

Max Activating Token Index: 202

Text #13

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7714. Min Act: -0.1700

Data Index: 99840 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7359. Min Act: -0.1700

Data Index: 5567631 (Open Web Text)

Max Activating Token Index: 899

Text #15

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.6978. Min Act: -0.1700

Data Index: 6522322 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7160. Min Act: -0.1700

Data Index: 3916349 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.7265. Min Act: -0.1700

Data Index: 5459295 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.6849. Min Act: -0.1700

Data Index: 4579265 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 3.9276. Min Range: -3.9276

Max Act: 3.6967. Min Act: -0.1700

Data Index: 672114 (Open Web Text)

Max Activating Token Index: 696