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

Dataset: Open Web Text

Neuron 2142 in Layer 3

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: 3.7942. Min Range: -3.7942

Max Act: 3.7942. Min Act: -0.1700

Data Index: 7289044 (Open Web Text)

Max Activating Token Index: 761

Text #1

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.7400. Min Act: -0.1700

Data Index: 2735122 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.6885. Min Act: -0.1700

Data Index: 5100476 (Open Web Text)

Max Activating Token Index: 649

Text #3

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.6306. Min Act: -0.1700

Data Index: 1690439 (Open Web Text)

Max Activating Token Index: 310

Text #4

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5908. Min Act: -0.1700

Data Index: 2422904 (Open Web Text)

Max Activating Token Index: 174

Text #5

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5658. Min Act: -0.1700

Data Index: 5839228 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5886. Min Act: -0.1700

Data Index: 4484890 (Open Web Text)

Max Activating Token Index: 28

Text #7

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5687. Min Act: -0.1700

Data Index: 3302878 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5833. Min Act: -0.1700

Data Index: 5244224 (Open Web Text)

Max Activating Token Index: 626

Text #9

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5335. Min Act: -0.1700

Data Index: 267305 (Open Web Text)

Max Activating Token Index: 744

Text #10

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5247. Min Act: -0.1700

Data Index: 3105949 (Open Web Text)

Max Activating Token Index: 487

Text #11

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5010. Min Act: -0.1700

Data Index: 8756018 (Open Web Text)

Max Activating Token Index: 150

Text #12

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.4993. Min Act: -0.1700

Data Index: 1435285 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.5222. Min Act: -0.1700

Data Index: 6852251 (Open Web Text)

Max Activating Token Index: 466

Text #14

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.4996. Min Act: -0.1700

Data Index: 7565794 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.4946. Min Act: -0.1700

Data Index: 5961175 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.4730. Min Act: -0.1700

Data Index: 5414944 (Open Web Text)

Max Activating Token Index: 796

Text #17

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.4898. Min Act: -0.1700

Data Index: 7331286 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.4825. Min Act: -0.1700

Data Index: 1493099 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 3.7942. Min Range: -3.7942

Max Act: 3.4812. Min Act: -0.1700

Data Index: 7598186 (Open Web Text)

Max Activating Token Index: 426