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

Dataset: Open Web Text

Neuron 2206 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: 3.6773. Min Range: -3.6773

Max Act: 3.6773. Min Act: -0.1700

Data Index: 4256458 (Open Web Text)

Max Activating Token Index: 967

Text #1

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.6469. Min Act: -0.1700

Data Index: 4483090 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.6081. Min Act: -0.1700

Data Index: 8662081 (Open Web Text)

Max Activating Token Index: 1012

Text #3

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.6246. Min Act: -0.1700

Data Index: 6206315 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5951. Min Act: -0.1700

Data Index: 1706703 (Open Web Text)

Max Activating Token Index: 363

Text #5

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5918. Min Act: -0.1700

Data Index: 128222 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5836. Min Act: -0.1700

Data Index: 7288104 (Open Web Text)

Max Activating Token Index: 587

Text #7

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5987. Min Act: -0.1700

Data Index: 5915720 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.6047. Min Act: -0.1700

Data Index: 3843597 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.6044. Min Act: -0.1700

Data Index: 6545817 (Open Web Text)

Max Activating Token Index: 434

Text #10

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5780. Min Act: -0.1700

Data Index: 619201 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5367. Min Act: -0.1700

Data Index: 4068527 (Open Web Text)

Max Activating Token Index: 433

Text #12

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5490. Min Act: -0.1700

Data Index: 5066556 (Open Web Text)

Max Activating Token Index: 714

Text #13

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5370. Min Act: -0.1700

Data Index: 2215 (Open Web Text)

Max Activating Token Index: 966

Text #14

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5213. Min Act: -0.1700

Data Index: 5173315 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5419. Min Act: -0.1700

Data Index: 287028 (Open Web Text)

Max Activating Token Index: 923

Text #16

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5179. Min Act: -0.1700

Data Index: 357672 (Open Web Text)

Max Activating Token Index: 1011

Text #17

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5083. Min Act: -0.1700

Data Index: 1593981 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5218. Min Act: -0.1700

Data Index: 6456492 (Open Web Text)

Max Activating Token Index: 732

Text #19

Max Range: 3.6773. Min Range: -3.6773

Max Act: 3.5242. Min Act: -0.1700

Data Index: 6613792 (Open Web Text)

Max Activating Token Index: 583