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

Dataset: Open Web Text

Neuron 1351 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: 3.9179. Min Range: -3.9179

Max Act: 3.9134. Min Act: -0.1700

Data Index: 3154029 (Open Web Text)

Max Activating Token Index: 156

Text #1

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.9179. Min Act: -0.1700

Data Index: 759117 (Open Web Text)

Max Activating Token Index: 628

Text #2

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8661. Min Act: -0.1700

Data Index: 3222133 (Open Web Text)

Max Activating Token Index: 185

Text #3

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.9039. Min Act: -0.1700

Data Index: 4585682 (Open Web Text)

Max Activating Token Index: 219

Text #4

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8986. Min Act: -0.1700

Data Index: 3177893 (Open Web Text)

Max Activating Token Index: 940

Text #5

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8787. Min Act: -0.1700

Data Index: 6140020 (Open Web Text)

Max Activating Token Index: 862

Text #6

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8520. Min Act: -0.1700

Data Index: 3224421 (Open Web Text)

Max Activating Token Index: 672

Text #7

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8629. Min Act: -0.1700

Data Index: 6395656 (Open Web Text)

Max Activating Token Index: 600

Text #8

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8146. Min Act: -0.1700

Data Index: 6971417 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8374. Min Act: -0.1700

Data Index: 8075265 (Open Web Text)

Max Activating Token Index: 219

Text #10

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8214. Min Act: -0.1700

Data Index: 2561826 (Open Web Text)

Max Activating Token Index: 643

Text #11

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8096. Min Act: -0.1700

Data Index: 5573198 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8074. Min Act: -0.1700

Data Index: 2787010 (Open Web Text)

Max Activating Token Index: 139

Text #13

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7845. Min Act: -0.1700

Data Index: 7206855 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7875. Min Act: -0.1700

Data Index: 1879459 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7893. Min Act: -0.1700

Data Index: 7410401 (Open Web Text)

Max Activating Token Index: 517

Text #16

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8117. Min Act: -0.1700

Data Index: 1055638 (Open Web Text)

Max Activating Token Index: 447

Text #17

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7692. Min Act: -0.1700

Data Index: 7988865 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8093. Min Act: -0.1700

Data Index: 6891997 (Open Web Text)

Max Activating Token Index: 453

Text #19

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8032. Min Act: -0.1700

Data Index: 5166112 (Open Web Text)

Max Activating Token Index: 5