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

Dataset: Open Web Text

Neuron 1618 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: 4.0235. Min Range: -4.0235

Max Act: 4.0235. Min Act: -0.1700

Data Index: 6722994 (Open Web Text)

Max Activating Token Index: 786

Text #1

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9920. Min Act: -0.1700

Data Index: 3356565 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9157. Min Act: -0.1700

Data Index: 1631114 (Open Web Text)

Max Activating Token Index: 744

Text #3

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9478. Min Act: -0.1700

Data Index: 60898 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8870. Min Act: -0.1700

Data Index: 913342 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9314. Min Act: -0.1700

Data Index: 8469132 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9433. Min Act: -0.1700

Data Index: 4086491 (Open Web Text)

Max Activating Token Index: 321

Text #7

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8025. Min Act: -0.1700

Data Index: 734017 (Open Web Text)

Max Activating Token Index: 80

Text #8

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8908. Min Act: -0.1700

Data Index: 1607392 (Open Web Text)

Max Activating Token Index: 358

Text #9

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9226. Min Act: -0.1700

Data Index: 6192849 (Open Web Text)

Max Activating Token Index: 339

Text #10

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8581. Min Act: -0.1700

Data Index: 7876607 (Open Web Text)

Max Activating Token Index: 587

Text #11

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.9161. Min Act: -0.1700

Data Index: 4708921 (Open Web Text)

Max Activating Token Index: 392

Text #12

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7998. Min Act: -0.1700

Data Index: 2606658 (Open Web Text)

Max Activating Token Index: 53

Text #13

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7680. Min Act: -0.1700

Data Index: 2024095 (Open Web Text)

Max Activating Token Index: 957

Text #14

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7995. Min Act: -0.1700

Data Index: 4742131 (Open Web Text)

Max Activating Token Index: 624

Text #15

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8215. Min Act: -0.1700

Data Index: 904496 (Open Web Text)

Max Activating Token Index: 259

Text #16

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7969. Min Act: -0.1700

Data Index: 5167750 (Open Web Text)

Max Activating Token Index: 440

Text #17

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8895. Min Act: -0.1700

Data Index: 6977655 (Open Web Text)

Max Activating Token Index: 303

Text #18

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.7372. Min Act: -0.1700

Data Index: 2425036 (Open Web Text)

Max Activating Token Index: 1005

Text #19

Max Range: 4.0235. Min Range: -4.0235

Max Act: 3.8122. Min Act: -0.1700

Data Index: 1893077 (Open Web Text)

Max Activating Token Index: 824