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

Dataset: Open Web Text

Neuron 2219 in Layer 5

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: 4.8243. Min Range: -4.8243

Max Act: 4.8238. Min Act: -0.1700

Data Index: 4550229 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.8243. Min Act: -0.1700

Data Index: 1765100 (Open Web Text)

Max Activating Token Index: 311

Text #2

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.7952. Min Act: -0.1700

Data Index: 2936464 (Open Web Text)

Max Activating Token Index: 576

Text #3

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.7476. Min Act: -0.1700

Data Index: 675202 (Open Web Text)

Max Activating Token Index: 432

Text #4

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.7085. Min Act: -0.1700

Data Index: 4842401 (Open Web Text)

Max Activating Token Index: 507

Text #5

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6974. Min Act: -0.1700

Data Index: 4827412 (Open Web Text)

Max Activating Token Index: 638

Text #6

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6811. Min Act: -0.1700

Data Index: 801477 (Open Web Text)

Max Activating Token Index: 334

Text #7

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6859. Min Act: -0.1700

Data Index: 4774078 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6752. Min Act: -0.1700

Data Index: 893183 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6515. Min Act: -0.1700

Data Index: 1268747 (Open Web Text)

Max Activating Token Index: 933

Text #10

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6358. Min Act: -0.1700

Data Index: 1446499 (Open Web Text)

Max Activating Token Index: 963

Text #11

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6164. Min Act: -0.1700

Data Index: 4676725 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6283. Min Act: -0.1700

Data Index: 5576585 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6458. Min Act: -0.1700

Data Index: 4557003 (Open Web Text)

Max Activating Token Index: 298

Text #14

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6208. Min Act: -0.1700

Data Index: 12957 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.5954. Min Act: -0.1700

Data Index: 1924351 (Open Web Text)

Max Activating Token Index: 221

Text #16

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6227. Min Act: -0.1700

Data Index: 1972939 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.5897. Min Act: -0.1700

Data Index: 871161 (Open Web Text)

Max Activating Token Index: 755

Text #18

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.6093. Min Act: -0.1700

Data Index: 3648087 (Open Web Text)

Max Activating Token Index: 788

Text #19

Max Range: 4.8243. Min Range: -4.8243

Max Act: 4.5951. Min Act: -0.1700

Data Index: 1806338 (Open Web Text)

Max Activating Token Index: 480