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

Dataset: Open Web Text

Neuron 476 in Layer 2

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: 2.7997. Min Range: -2.7997

Max Act: 2.7997. Min Act: -0.1700

Data Index: 4158669 (Open Web Text)

Max Activating Token Index: 886

Text #1

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.7859. Min Act: -0.1700

Data Index: 6297726 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.7677. Min Act: -0.1700

Data Index: 3369021 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.7395. Min Act: -0.1700

Data Index: 6815556 (Open Web Text)

Max Activating Token Index: 371

Text #4

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.7329. Min Act: -0.1700

Data Index: 1898455 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.7197. Min Act: -0.1700

Data Index: 2975171 (Open Web Text)

Max Activating Token Index: 687

Text #6

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.7118. Min Act: -0.1700

Data Index: 8766709 (Open Web Text)

Max Activating Token Index: 346

Text #7

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6857. Min Act: -0.1700

Data Index: 2361006 (Open Web Text)

Max Activating Token Index: 819

Text #8

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6832. Min Act: -0.1700

Data Index: 3415963 (Open Web Text)

Max Activating Token Index: 724

Text #9

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.7303. Min Act: -0.1700

Data Index: 2494961 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6665. Min Act: -0.1700

Data Index: 6872396 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6921. Min Act: -0.1700

Data Index: 2835638 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6751. Min Act: -0.1700

Data Index: 5956903 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.7110. Min Act: -0.1700

Data Index: 7809865 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6432. Min Act: -0.1700

Data Index: 495347 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6632. Min Act: -0.1700

Data Index: 6084702 (Open Web Text)

Max Activating Token Index: 711

Text #16

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6884. Min Act: -0.1700

Data Index: 1282723 (Open Web Text)

Max Activating Token Index: 947

Text #17

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6447. Min Act: -0.1700

Data Index: 6679477 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6733. Min Act: -0.1700

Data Index: 138155 (Open Web Text)

Max Activating Token Index: 956

Text #19

Max Range: 2.7997. Min Range: -2.7997

Max Act: 2.6507. Min Act: -0.1700

Data Index: 2158351 (Open Web Text)

Max Activating Token Index: 37