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

Dataset: Open Web Text

Neuron 1523 in Layer 1

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: 0.9172. Min Range: -0.9172

Max Act: 0.9149. Min Act: -0.1700

Data Index: 7555513 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.9172. Min Act: -0.1700

Data Index: 4394074 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.9047. Min Act: -0.1700

Data Index: 1594240 (Open Web Text)

Max Activating Token Index: 1008

Text #3

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.9003. Min Act: -0.1700

Data Index: 1013605 (Open Web Text)

Max Activating Token Index: 1008

Text #4

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.9041. Min Act: -0.1700

Data Index: 8719948 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.9002. Min Act: -0.1700

Data Index: 7386470 (Open Web Text)

Max Activating Token Index: 1005

Text #6

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.9096. Min Act: -0.1700

Data Index: 161576 (Open Web Text)

Max Activating Token Index: 1010

Text #7

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8853. Min Act: -0.1700

Data Index: 8522036 (Open Web Text)

Max Activating Token Index: 1006

Text #8

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8799. Min Act: -0.1700

Data Index: 2124044 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8818. Min Act: -0.1700

Data Index: 1787950 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8914. Min Act: -0.1700

Data Index: 970206 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8873. Min Act: -0.1700

Data Index: 7117528 (Open Web Text)

Max Activating Token Index: 1008

Text #12

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8724. Min Act: -0.1700

Data Index: 6330412 (Open Web Text)

Max Activating Token Index: 1005

Text #13

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8782. Min Act: -0.1700

Data Index: 8665985 (Open Web Text)

Max Activating Token Index: 1012

Text #14

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8737. Min Act: -0.1700

Data Index: 2828478 (Open Web Text)

Max Activating Token Index: 1015

Text #15

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8611. Min Act: -0.1700

Data Index: 4514350 (Open Web Text)

Max Activating Token Index: 1000

Text #16

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8628. Min Act: -0.1700

Data Index: 6344864 (Open Web Text)

Max Activating Token Index: 1010

Text #17

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8598. Min Act: -0.1700

Data Index: 3607270 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8662. Min Act: -0.1700

Data Index: 5599407 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 0.9172. Min Range: -0.9172

Max Act: 0.8644. Min Act: -0.1700

Data Index: 4792637 (Open Web Text)

Max Activating Token Index: 1007