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

Dataset: Open Web Text

Neuron 1097 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: 4.7715. Min Range: -4.7715

Max Act: 4.7715. Min Act: -0.1700

Data Index: 2383262 (Open Web Text)

Max Activating Token Index: 572

Text #1

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.7207. Min Act: -0.1700

Data Index: 564194 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.7169. Min Act: -0.1700

Data Index: 1487991 (Open Web Text)

Max Activating Token Index: 486

Text #3

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6483. Min Act: -0.1700

Data Index: 5052228 (Open Web Text)

Max Activating Token Index: 201

Text #4

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6214. Min Act: -0.1700

Data Index: 6421926 (Open Web Text)

Max Activating Token Index: 686

Text #5

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6439. Min Act: -0.1700

Data Index: 4972051 (Open Web Text)

Max Activating Token Index: 178

Text #6

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6527. Min Act: -0.1700

Data Index: 457339 (Open Web Text)

Max Activating Token Index: 536

Text #7

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6141. Min Act: -0.1700

Data Index: 4818954 (Open Web Text)

Max Activating Token Index: 769

Text #8

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6316. Min Act: -0.1700

Data Index: 3240665 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6349. Min Act: -0.1700

Data Index: 6371543 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6229. Min Act: -0.1700

Data Index: 6941654 (Open Web Text)

Max Activating Token Index: 175

Text #11

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6219. Min Act: -0.1700

Data Index: 3577381 (Open Web Text)

Max Activating Token Index: 286

Text #12

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6029. Min Act: -0.1700

Data Index: 1378922 (Open Web Text)

Max Activating Token Index: 610

Text #13

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.5899. Min Act: -0.1700

Data Index: 2172613 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6160. Min Act: -0.1700

Data Index: 2309838 (Open Web Text)

Max Activating Token Index: 809

Text #15

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.6297. Min Act: -0.1700

Data Index: 6901789 (Open Web Text)

Max Activating Token Index: 879

Text #16

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.5320. Min Act: -0.1700

Data Index: 3240666 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.5862. Min Act: -0.1700

Data Index: 288536 (Open Web Text)

Max Activating Token Index: 319

Text #18

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.5578. Min Act: -0.1700

Data Index: 3294581 (Open Web Text)

Max Activating Token Index: 469

Text #19

Max Range: 4.7715. Min Range: -4.7715

Max Act: 4.5761. Min Act: -0.1700

Data Index: 2062734 (Open Web Text)

Max Activating Token Index: 521