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

Dataset: Open Web Text

Neuron 1242 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: 4.4362. Min Range: -4.4362

Max Act: 4.4362. Min Act: -0.1700

Data Index: 4662600 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3955. Min Act: -0.1700

Data Index: 5845269 (Open Web Text)

Max Activating Token Index: 705

Text #2

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3829. Min Act: -0.1700

Data Index: 2030201 (Open Web Text)

Max Activating Token Index: 697

Text #3

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3472. Min Act: -0.1700

Data Index: 7847528 (Open Web Text)

Max Activating Token Index: 318

Text #4

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3234. Min Act: -0.1700

Data Index: 3822775 (Open Web Text)

Max Activating Token Index: 115

Text #5

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3323. Min Act: -0.1700

Data Index: 3547969 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3476. Min Act: -0.1700

Data Index: 3460829 (Open Web Text)

Max Activating Token Index: 508

Text #7

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3015. Min Act: -0.1700

Data Index: 5159543 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3346. Min Act: -0.1700

Data Index: 7713290 (Open Web Text)

Max Activating Token Index: 769

Text #9

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3161. Min Act: -0.1700

Data Index: 7865350 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2332. Min Act: -0.1700

Data Index: 8249088 (Open Web Text)

Max Activating Token Index: 543

Text #11

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2465. Min Act: -0.1700

Data Index: 8192279 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2474. Min Act: -0.1700

Data Index: 6102956 (Open Web Text)

Max Activating Token Index: 394

Text #13

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2112. Min Act: -0.1700

Data Index: 815344 (Open Web Text)

Max Activating Token Index: 527

Text #14

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2096. Min Act: -0.1700

Data Index: 5762415 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2291. Min Act: -0.1700

Data Index: 1240540 (Open Web Text)

Max Activating Token Index: 634

Text #16

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2252. Min Act: -0.1700

Data Index: 8825346 (Open Web Text)

Max Activating Token Index: 407

Text #17

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.1602. Min Act: -0.1700

Data Index: 5801067 (Open Web Text)

Max Activating Token Index: 426

Text #18

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.1653. Min Act: -0.1700

Data Index: 2523194 (Open Web Text)

Max Activating Token Index: 228

Text #19

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.1535. Min Act: -0.1700

Data Index: 6478453 (Open Web Text)

Max Activating Token Index: 920