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

Dataset: Open Web Text

Neuron 1533 in Layer 2

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: 3.6215. Min Range: -3.6215

Max Act: 3.6058. Min Act: -0.1700

Data Index: 1521775 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.6215. Min Act: -0.1700

Data Index: 5642459 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.6171. Min Act: -0.1700

Data Index: 1090626 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5690. Min Act: -0.1700

Data Index: 1305164 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5785. Min Act: -0.1700

Data Index: 3999556 (Open Web Text)

Max Activating Token Index: 474

Text #5

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5463. Min Act: -0.1700

Data Index: 5177663 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5278. Min Act: -0.1700

Data Index: 1273739 (Open Web Text)

Max Activating Token Index: 283

Text #7

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5464. Min Act: -0.1700

Data Index: 4105792 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5499. Min Act: -0.1700

Data Index: 7696208 (Open Web Text)

Max Activating Token Index: 841

Text #9

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5511. Min Act: -0.1700

Data Index: 914159 (Open Web Text)

Max Activating Token Index: 747

Text #10

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5508. Min Act: -0.1700

Data Index: 5961718 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5330. Min Act: -0.1700

Data Index: 1894458 (Open Web Text)

Max Activating Token Index: 400

Text #12

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5346. Min Act: -0.1700

Data Index: 1701183 (Open Web Text)

Max Activating Token Index: 776

Text #13

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5112. Min Act: -0.1700

Data Index: 2036767 (Open Web Text)

Max Activating Token Index: 204

Text #14

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5101. Min Act: -0.1700

Data Index: 983936 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5191. Min Act: -0.1700

Data Index: 994313 (Open Web Text)

Max Activating Token Index: 257

Text #16

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5069. Min Act: -0.1700

Data Index: 2488489 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.5193. Min Act: -0.1700

Data Index: 484757 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.4989. Min Act: -0.1700

Data Index: 2975389 (Open Web Text)

Max Activating Token Index: 421

Text #19

Max Range: 3.6215. Min Range: -3.6215

Max Act: 3.4913. Min Act: -0.1700

Data Index: 4895265 (Open Web Text)

Max Activating Token Index: 385