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

Dataset: Open Web Text

Neuron 834 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: 1.1756. Min Range: -1.1756

Max Act: 1.1756. Min Act: -0.1699

Data Index: 3118801 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1463. Min Act: -0.1696

Data Index: 3881564 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1329. Min Act: -0.1700

Data Index: 1690640 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1334. Min Act: -0.1698

Data Index: 4420567 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1277. Min Act: -0.1698

Data Index: 2570881 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1110. Min Act: -0.1697

Data Index: 5478560 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1113. Min Act: -0.1700

Data Index: 7781452 (Open Web Text)

Max Activating Token Index: 1019

Text #7

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1097. Min Act: -0.1698

Data Index: 7352617 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1061. Min Act: -0.1699

Data Index: 4896873 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1072. Min Act: -0.1698

Data Index: 578857 (Open Web Text)

Max Activating Token Index: 1020

Text #10

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1142. Min Act: -0.1700

Data Index: 4606994 (Open Web Text)

Max Activating Token Index: 1018

Text #11

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0967. Min Act: -0.1698

Data Index: 1902264 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1002. Min Act: -0.1699

Data Index: 5177553 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1103. Min Act: -0.1700

Data Index: 8648826 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0900. Min Act: -0.1700

Data Index: 3893693 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0971. Min Act: -0.1698

Data Index: 8238613 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0889. Min Act: -0.1700

Data Index: 7494116 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0770. Min Act: -0.1699

Data Index: 1369636 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0847. Min Act: -0.1699

Data Index: 2668402 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0808. Min Act: -0.1700

Data Index: 7140198 (Open Web Text)

Max Activating Token Index: 1022