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

Dataset: Open Web Text

Neuron 1357 in Layer 5

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: 4.1309. Min Range: -4.1309

Max Act: 4.1309. Min Act: -0.1700

Data Index: 4699778 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 4.1309. Min Range: -4.1309

Max Act: 4.1275. Min Act: -0.1700

Data Index: 1610893 (Open Web Text)

Max Activating Token Index: 500

Text #2

Max Range: 4.1309. Min Range: -4.1309

Max Act: 4.0606. Min Act: -0.1700

Data Index: 4434138 (Open Web Text)

Max Activating Token Index: 682

Text #3

Max Range: 4.1309. Min Range: -4.1309

Max Act: 4.0818. Min Act: -0.1700

Data Index: 3227836 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 4.1309. Min Range: -4.1309

Max Act: 4.0344. Min Act: -0.1700

Data Index: 8609379 (Open Web Text)

Max Activating Token Index: 304

Text #5

Max Range: 4.1309. Min Range: -4.1309

Max Act: 4.0531. Min Act: -0.1700

Data Index: 3227837 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 4.1309. Min Range: -4.1309

Max Act: 4.0012. Min Act: -0.1700

Data Index: 6551187 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 4.1309. Min Range: -4.1309

Max Act: 4.0250. Min Act: -0.1700

Data Index: 2790279 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9602. Min Act: -0.1700

Data Index: 5985069 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9822. Min Act: -0.1700

Data Index: 230070 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9998. Min Act: -0.1700

Data Index: 2432153 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9851. Min Act: -0.1700

Data Index: 932663 (Open Web Text)

Max Activating Token Index: 552

Text #12

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9678. Min Act: -0.1700

Data Index: 3126977 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9647. Min Act: -0.1700

Data Index: 5035381 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9261. Min Act: -0.1700

Data Index: 5996764 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9358. Min Act: -0.1700

Data Index: 843140 (Open Web Text)

Max Activating Token Index: 974

Text #16

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9371. Min Act: -0.1700

Data Index: 6050486 (Open Web Text)

Max Activating Token Index: 957

Text #17

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9183. Min Act: -0.1700

Data Index: 1632249 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9069. Min Act: -0.1700

Data Index: 6290588 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 4.1309. Min Range: -4.1309

Max Act: 3.9181. Min Act: -0.1700

Data Index: 4626065 (Open Web Text)

Max Activating Token Index: 986