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

Dataset: Open Web Text

Neuron 2126 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: 4.6039. Min Range: -4.6039

Max Act: 4.5455. Min Act: -0.1700

Data Index: 2659427 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5509. Min Act: -0.1700

Data Index: 489675 (Open Web Text)

Max Activating Token Index: 714

Text #2

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5556. Min Act: -0.1700

Data Index: 4090045 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.6039. Min Act: -0.1700

Data Index: 7979267 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5721. Min Act: -0.1700

Data Index: 3339730 (Open Web Text)

Max Activating Token Index: 936

Text #5

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5012. Min Act: -0.1700

Data Index: 4392387 (Open Web Text)

Max Activating Token Index: 1009

Text #6

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5474. Min Act: -0.1700

Data Index: 4138568 (Open Web Text)

Max Activating Token Index: 741

Text #7

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5312. Min Act: -0.1700

Data Index: 415946 (Open Web Text)

Max Activating Token Index: 915

Text #8

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5040. Min Act: -0.1700

Data Index: 8352593 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5109. Min Act: -0.1700

Data Index: 1652298 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5222. Min Act: -0.1700

Data Index: 4616410 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.4980. Min Act: -0.1700

Data Index: 6123842 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5120. Min Act: -0.1700

Data Index: 6456087 (Open Web Text)

Max Activating Token Index: 966

Text #13

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5032. Min Act: -0.1700

Data Index: 1973334 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5250. Min Act: -0.1700

Data Index: 2081597 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5020. Min Act: -0.1700

Data Index: 6697831 (Open Web Text)

Max Activating Token Index: 899

Text #16

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.4922. Min Act: -0.1700

Data Index: 7709397 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5168. Min Act: -0.1700

Data Index: 2435829 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.5325. Min Act: -0.1700

Data Index: 8107564 (Open Web Text)

Max Activating Token Index: 447

Text #19

Max Range: 4.6039. Min Range: -4.6039

Max Act: 4.4881. Min Act: -0.1700

Data Index: 2646610 (Open Web Text)

Max Activating Token Index: 955