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

Dataset: Open Web Text

Neuron 699 in Layer 0

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: 0.8126. Min Range: -0.8126

Max Act: 0.8126. Min Act: -0.1700

Data Index: 3434712 (Open Web Text)

Max Activating Token Index: 683

Text #1

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.8103. Min Act: -0.1700

Data Index: 3604454 (Open Web Text)

Max Activating Token Index: 651

Text #2

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.8021. Min Act: -0.1700

Data Index: 2331095 (Open Web Text)

Max Activating Token Index: 665

Text #3

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.8046. Min Act: -0.1700

Data Index: 8303505 (Open Web Text)

Max Activating Token Index: 672

Text #4

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.8028. Min Act: -0.1700

Data Index: 4682057 (Open Web Text)

Max Activating Token Index: 685

Text #5

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.8051. Min Act: -0.1700

Data Index: 4729916 (Open Web Text)

Max Activating Token Index: 669

Text #6

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7987. Min Act: -0.1700

Data Index: 4921484 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.8018. Min Act: -0.1700

Data Index: 4564676 (Open Web Text)

Max Activating Token Index: 639

Text #8

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.8065. Min Act: -0.1700

Data Index: 3676205 (Open Web Text)

Max Activating Token Index: 674

Text #9

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7915. Min Act: -0.1700

Data Index: 3289673 (Open Web Text)

Max Activating Token Index: 666

Text #10

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7931. Min Act: -0.1700

Data Index: 1110130 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7914. Min Act: -0.1700

Data Index: 2293836 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7968. Min Act: -0.1700

Data Index: 5870401 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7934. Min Act: -0.1700

Data Index: 497286 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7869. Min Act: -0.1700

Data Index: 337766 (Open Web Text)

Max Activating Token Index: 669

Text #15

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7841. Min Act: -0.1700

Data Index: 6304058 (Open Web Text)

Max Activating Token Index: 681

Text #16

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7802. Min Act: -0.1700

Data Index: 3761001 (Open Web Text)

Max Activating Token Index: 660

Text #17

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7893. Min Act: -0.1700

Data Index: 5260141 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7882. Min Act: -0.1700

Data Index: 623062 (Open Web Text)

Max Activating Token Index: 674

Text #19

Max Range: 0.8126. Min Range: -0.8126

Max Act: 0.7771. Min Act: -0.1700

Data Index: 1296236 (Open Web Text)

Max Activating Token Index: 655