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

Dataset: Open Web Text

Neuron 2039 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: 1.9356. Min Range: -1.9356

Max Act: 1.9308. Min Act: -0.1700

Data Index: 4567124 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9293. Min Act: -0.1700

Data Index: 247255 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9356. Min Act: -0.1700

Data Index: 2264296 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9338. Min Act: -0.1700

Data Index: 8114777 (Open Web Text)

Max Activating Token Index: 346

Text #4

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8953. Min Act: -0.1700

Data Index: 4864051 (Open Web Text)

Max Activating Token Index: 394

Text #5

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9056. Min Act: -0.1700

Data Index: 4813375 (Open Web Text)

Max Activating Token Index: 331

Text #6

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9085. Min Act: -0.1699

Data Index: 2724495 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9143. Min Act: -0.1700

Data Index: 7613291 (Open Web Text)

Max Activating Token Index: 443

Text #8

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9005. Min Act: -0.1700

Data Index: 7072653 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8988. Min Act: -0.1700

Data Index: 5113747 (Open Web Text)

Max Activating Token Index: 338

Text #10

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9090. Min Act: -0.1700

Data Index: 8516953 (Open Web Text)

Max Activating Token Index: 354

Text #11

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.9094. Min Act: -0.1700

Data Index: 8193709 (Open Web Text)

Max Activating Token Index: 894

Text #12

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8882. Min Act: -0.1700

Data Index: 5541126 (Open Web Text)

Max Activating Token Index: 192

Text #13

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8936. Min Act: -0.1700

Data Index: 6253989 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8975. Min Act: -0.1700

Data Index: 1458735 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8957. Min Act: -0.1695

Data Index: 558349 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8908. Min Act: -0.1700

Data Index: 2871025 (Open Web Text)

Max Activating Token Index: 357

Text #17

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8998. Min Act: -0.1700

Data Index: 51874 (Open Web Text)

Max Activating Token Index: 198

Text #18

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8862. Min Act: -0.1700

Data Index: 7859614 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 1.9356. Min Range: -1.9356

Max Act: 1.8965. Min Act: -0.1700

Data Index: 1383288 (Open Web Text)

Max Activating Token Index: 541