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

Dataset: Open Web Text

Neuron 2563 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: 3.0006. Min Range: -3.0006

Max Act: 3.0006. Min Act: -0.1700

Data Index: 1667247 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9982. Min Act: -0.1700

Data Index: 1323123 (Open Web Text)

Max Activating Token Index: 179

Text #2

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9829. Min Act: -0.1700

Data Index: 3540686 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9302. Min Act: -0.1700

Data Index: 8188464 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9325. Min Act: -0.1700

Data Index: 4658256 (Open Web Text)

Max Activating Token Index: 168

Text #5

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9174. Min Act: -0.1700

Data Index: 93118 (Open Web Text)

Max Activating Token Index: 537

Text #6

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9139. Min Act: -0.1700

Data Index: 2928608 (Open Web Text)

Max Activating Token Index: 162

Text #7

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9132. Min Act: -0.1700

Data Index: 7289797 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9100. Min Act: -0.1700

Data Index: 2845398 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9189. Min Act: -0.1700

Data Index: 1379229 (Open Web Text)

Max Activating Token Index: 324

Text #10

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.8843. Min Act: -0.1700

Data Index: 8174159 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.8948. Min Act: -0.1700

Data Index: 179923 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.8840. Min Act: -0.1700

Data Index: 4975882 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.8939. Min Act: -0.1700

Data Index: 8001424 (Open Web Text)

Max Activating Token Index: 411

Text #14

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.8944. Min Act: -0.1700

Data Index: 7487698 (Open Web Text)

Max Activating Token Index: 52

Text #15

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9043. Min Act: -0.1700

Data Index: 89403 (Open Web Text)

Max Activating Token Index: 227

Text #16

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.8929. Min Act: -0.1700

Data Index: 4929447 (Open Web Text)

Max Activating Token Index: 112

Text #17

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.8847. Min Act: -0.1700

Data Index: 6613854 (Open Web Text)

Max Activating Token Index: 988

Text #18

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.8875. Min Act: -0.1700

Data Index: 2560171 (Open Web Text)

Max Activating Token Index: 276

Text #19

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.9025. Min Act: -0.1700

Data Index: 6236709 (Open Web Text)

Max Activating Token Index: 511