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

Dataset: Open Web Text

Neuron 1326 in Layer 4

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: 2.7162. Min Range: -2.7162

Max Act: 2.7162. Min Act: -0.1700

Data Index: 1934235 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.7162. Min Act: -0.1700

Data Index: 7013287 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.7162. Min Act: -0.1700

Data Index: 5235646 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.7162. Min Act: -0.1700

Data Index: 5248307 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.6890. Min Act: -0.1700

Data Index: 1611696 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.6890. Min Act: -0.1700

Data Index: 5604088 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5933. Min Act: -0.1700

Data Index: 8079351 (Open Web Text)

Max Activating Token Index: 864

Text #7

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.6191. Min Act: -0.1700

Data Index: 6341064 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5822. Min Act: -0.1700

Data Index: 5180397 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5822. Min Act: -0.1700

Data Index: 55383 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5705. Min Act: -0.1700

Data Index: 1179688 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5936. Min Act: -0.1700

Data Index: 4282336 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5150. Min Act: -0.1700

Data Index: 8509279 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.4841. Min Act: -0.1700

Data Index: 8640210 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5169. Min Act: -0.1700

Data Index: 3039406 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5032. Min Act: -0.1700

Data Index: 5824064 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.4748. Min Act: -0.1700

Data Index: 5031139 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.5019. Min Act: -0.1700

Data Index: 6211116 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.4580. Min Act: -0.1700

Data Index: 6479396 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.7162. Min Range: -2.7162

Max Act: 2.4727. Min Act: -0.1700

Data Index: 7477109 (Open Web Text)

Max Activating Token Index: 3