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

Dataset: Open Web Text

Neuron 2151 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: 4.9367. Min Range: -4.9367

Max Act: 4.9367. Min Act: -0.1700

Data Index: 2307788 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7877. Min Act: -0.1700

Data Index: 6301714 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7591. Min Act: -0.1700

Data Index: 211718 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7601. Min Act: -0.1700

Data Index: 4544842 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7705. Min Act: -0.1700

Data Index: 5494820 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7432. Min Act: -0.1700

Data Index: 4774245 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7478. Min Act: -0.1700

Data Index: 4697599 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7074. Min Act: -0.1700

Data Index: 5746082 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7152. Min Act: -0.1700

Data Index: 4984033 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7088. Min Act: -0.1700

Data Index: 932913 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7103. Min Act: -0.1700

Data Index: 664829 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7002. Min Act: -0.1700

Data Index: 7889731 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7076. Min Act: -0.1700

Data Index: 6892990 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.6948. Min Act: -0.1700

Data Index: 6827928 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.6667. Min Act: -0.1700

Data Index: 226838 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.6670. Min Act: -0.1700

Data Index: 3308360 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.7001. Min Act: -0.1700

Data Index: 5202551 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.6792. Min Act: -0.1700

Data Index: 5118926 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.6673. Min Act: -0.1700

Data Index: 4667912 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.9367. Min Range: -4.9367

Max Act: 4.6710. Min Act: -0.1700

Data Index: 2469657 (Open Web Text)

Max Activating Token Index: 5