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

Dataset: Open Web Text

Neuron 3004 in Layer 2

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: 3.9688. Min Range: -3.9688

Max Act: 3.9637. Min Act: -0.1700

Data Index: 2425811 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9688. Min Act: -0.1700

Data Index: 506056 (Open Web Text)

Max Activating Token Index: 79

Text #2

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9345. Min Act: -0.1700

Data Index: 4604652 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9327. Min Act: -0.1700

Data Index: 5767965 (Open Web Text)

Max Activating Token Index: 142

Text #4

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9158. Min Act: -0.1700

Data Index: 6450376 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9031. Min Act: -0.1700

Data Index: 763863 (Open Web Text)

Max Activating Token Index: 736

Text #6

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9236. Min Act: -0.1700

Data Index: 1965112 (Open Web Text)

Max Activating Token Index: 837

Text #7

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9150. Min Act: -0.1700

Data Index: 8766514 (Open Web Text)

Max Activating Token Index: 335

Text #8

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9268. Min Act: -0.1700

Data Index: 2694695 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9123. Min Act: -0.1700

Data Index: 8156123 (Open Web Text)

Max Activating Token Index: 265

Text #10

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9157. Min Act: -0.1700

Data Index: 905768 (Open Web Text)

Max Activating Token Index: 888

Text #11

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9173. Min Act: -0.1700

Data Index: 5169347 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9013. Min Act: -0.1700

Data Index: 4930324 (Open Web Text)

Max Activating Token Index: 224

Text #13

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9205. Min Act: -0.1700

Data Index: 4898429 (Open Web Text)

Max Activating Token Index: 163

Text #14

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.8994. Min Act: -0.1700

Data Index: 4253027 (Open Web Text)

Max Activating Token Index: 284

Text #15

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9060. Min Act: -0.1700

Data Index: 161737 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9129. Min Act: -0.1700

Data Index: 3523921 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9007. Min Act: -0.1700

Data Index: 107950 (Open Web Text)

Max Activating Token Index: 299

Text #18

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.9006. Min Act: -0.1700

Data Index: 2792482 (Open Web Text)

Max Activating Token Index: 199

Text #19

Max Range: 3.9688. Min Range: -3.9688

Max Act: 3.8770. Min Act: -0.1700

Data Index: 2798156 (Open Web Text)

Max Activating Token Index: 392