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

Dataset: Open Web Text

Neuron 2038 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: 2.9070. Min Range: -2.9070

Max Act: 2.9070. Min Act: -0.1700

Data Index: 5183278 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.9055. Min Act: -0.1700

Data Index: 4363475 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8934. Min Act: -0.1700

Data Index: 8568454 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8462. Min Act: -0.1700

Data Index: 3620465 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8462. Min Act: -0.1700

Data Index: 8620404 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8368. Min Act: -0.1700

Data Index: 7988285 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8409. Min Act: -0.1700

Data Index: 5410629 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8363. Min Act: -0.1700

Data Index: 4774050 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8277. Min Act: -0.1700

Data Index: 1268718 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8209. Min Act: -0.1700

Data Index: 4580779 (Open Web Text)

Max Activating Token Index: 54

Text #10

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8264. Min Act: -0.1700

Data Index: 4401305 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8330. Min Act: -0.1700

Data Index: 7799727 (Open Web Text)

Max Activating Token Index: 44

Text #12

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8266. Min Act: -0.1700

Data Index: 7579756 (Open Web Text)

Max Activating Token Index: 871

Text #13

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8303. Min Act: -0.1700

Data Index: 4128119 (Open Web Text)

Max Activating Token Index: 351

Text #14

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8072. Min Act: -0.1700

Data Index: 2394316 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8091. Min Act: -0.1700

Data Index: 964900 (Open Web Text)

Max Activating Token Index: 147

Text #16

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8214. Min Act: -0.1700

Data Index: 3201786 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8092. Min Act: -0.1700

Data Index: 3830122 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8117. Min Act: -0.1700

Data Index: 3117350 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 2.9070. Min Range: -2.9070

Max Act: 2.8125. Min Act: -0.1700

Data Index: 5011435 (Open Web Text)

Max Activating Token Index: 3