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

Dataset: Open Web Text

Neuron 2830 in Layer 4

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: 3.9235. Min Range: -3.9235

Max Act: 3.8913. Min Act: -0.1700

Data Index: 3385715 (Open Web Text)

Max Activating Token Index: 669

Text #1

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.8627. Min Act: -0.1700

Data Index: 3070945 (Open Web Text)

Max Activating Token Index: 855

Text #2

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.9235. Min Act: -0.1700

Data Index: 101486 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.8939. Min Act: -0.1700

Data Index: 7285705 (Open Web Text)

Max Activating Token Index: 930

Text #4

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7884. Min Act: -0.1700

Data Index: 8636452 (Open Web Text)

Max Activating Token Index: 145

Text #5

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.8536. Min Act: -0.1700

Data Index: 1099245 (Open Web Text)

Max Activating Token Index: 302

Text #6

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.8699. Min Act: -0.1700

Data Index: 6720763 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7726. Min Act: -0.1700

Data Index: 1685593 (Open Web Text)

Max Activating Token Index: 475

Text #8

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7979. Min Act: -0.1700

Data Index: 8691435 (Open Web Text)

Max Activating Token Index: 427

Text #9

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.8271. Min Act: -0.1700

Data Index: 5976669 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.8378. Min Act: -0.1700

Data Index: 3487246 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.8233. Min Act: -0.1700

Data Index: 8666685 (Open Web Text)

Max Activating Token Index: 422

Text #12

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.8117. Min Act: -0.1700

Data Index: 8497579 (Open Web Text)

Max Activating Token Index: 228

Text #13

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7989. Min Act: -0.1700

Data Index: 1384156 (Open Web Text)

Max Activating Token Index: 337

Text #14

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7660. Min Act: -0.1700

Data Index: 6522215 (Open Web Text)

Max Activating Token Index: 290

Text #15

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7703. Min Act: -0.1700

Data Index: 3550260 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7197. Min Act: -0.1700

Data Index: 8799473 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7500. Min Act: -0.1700

Data Index: 8109764 (Open Web Text)

Max Activating Token Index: 357

Text #18

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7691. Min Act: -0.1700

Data Index: 748118 (Open Web Text)

Max Activating Token Index: 621

Text #19

Max Range: 3.9235. Min Range: -3.9235

Max Act: 3.7662. Min Act: -0.1700

Data Index: 6584976 (Open Web Text)

Max Activating Token Index: 1016