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

Dataset: Open Web Text

Neuron 377 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: 2.1951. Min Range: -2.1951

Max Act: 2.1951. Min Act: -0.1699

Data Index: 1418140 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.1151. Min Act: -0.1700

Data Index: 2551116 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.1144. Min Act: -0.1700

Data Index: 5208238 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0858. Min Act: -0.1700

Data Index: 1418139 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0602. Min Act: -0.1700

Data Index: 757841 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0715. Min Act: -0.1699

Data Index: 1332643 (Open Web Text)

Max Activating Token Index: 90

Text #6

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0591. Min Act: -0.1700

Data Index: 2938317 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0552. Min Act: -0.1700

Data Index: 1418138 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0455. Min Act: -0.1700

Data Index: 1418136 (Open Web Text)

Max Activating Token Index: 37

Text #9

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0346. Min Act: -0.1700

Data Index: 6261386 (Open Web Text)

Max Activating Token Index: 48

Text #10

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0276. Min Act: -0.1700

Data Index: 5266683 (Open Web Text)

Max Activating Token Index: 650

Text #11

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0099. Min Act: -0.1700

Data Index: 8207899 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0217. Min Act: -0.1700

Data Index: 1418135 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0146. Min Act: -0.1700

Data Index: 2500797 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0111. Min Act: -0.1700

Data Index: 1418141 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 2.1951. Min Range: -2.1951

Max Act: 2.0189. Min Act: -0.1700

Data Index: 1418137 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 2.1951. Min Range: -2.1951

Max Act: 1.9950. Min Act: -0.1700

Data Index: 7156457 (Open Web Text)

Max Activating Token Index: 564

Text #17

Max Range: 2.1951. Min Range: -2.1951

Max Act: 1.9931. Min Act: -0.1700

Data Index: 1332642 (Open Web Text)

Max Activating Token Index: 110

Text #18

Max Range: 2.1951. Min Range: -2.1951

Max Act: 1.9713. Min Act: -0.1700

Data Index: 4491234 (Open Web Text)

Max Activating Token Index: 871

Text #19

Max Range: 2.1951. Min Range: -2.1951

Max Act: 1.9898. Min Act: -0.1700

Data Index: 1418134 (Open Web Text)

Max Activating Token Index: 139