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

Dataset: Open Web Text

Neuron 2740 in Layer 6

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: 4.6726. Min Range: -4.6726

Max Act: 4.6726. Min Act: -0.1700

Data Index: 4573832 (Open Web Text)

Max Activating Token Index: 682

Text #1

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6462. Min Act: -0.1700

Data Index: 1395109 (Open Web Text)

Max Activating Token Index: 634

Text #2

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.6067. Min Act: -0.1700

Data Index: 7080662 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5589. Min Act: -0.1700

Data Index: 224289 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5627. Min Act: -0.1700

Data Index: 476982 (Open Web Text)

Max Activating Token Index: 991

Text #5

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5596. Min Act: -0.1700

Data Index: 7006969 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5386. Min Act: -0.1700

Data Index: 1739937 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.5087. Min Act: -0.1700

Data Index: 1158095 (Open Web Text)

Max Activating Token Index: 923

Text #8

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4881. Min Act: -0.1700

Data Index: 6450781 (Open Web Text)

Max Activating Token Index: 172

Text #9

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4938. Min Act: -0.1700

Data Index: 796056 (Open Web Text)

Max Activating Token Index: 347

Text #10

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4443. Min Act: -0.1700

Data Index: 5139709 (Open Web Text)

Max Activating Token Index: 658

Text #11

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4829. Min Act: -0.1700

Data Index: 5373537 (Open Web Text)

Max Activating Token Index: 262

Text #12

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4500. Min Act: -0.1700

Data Index: 5729286 (Open Web Text)

Max Activating Token Index: 476

Text #13

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4458. Min Act: -0.1700

Data Index: 1369799 (Open Web Text)

Max Activating Token Index: 846

Text #14

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4488. Min Act: -0.1700

Data Index: 4936177 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4571. Min Act: -0.1700

Data Index: 2814010 (Open Web Text)

Max Activating Token Index: 720

Text #16

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4375. Min Act: -0.1700

Data Index: 8111435 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4502. Min Act: -0.1700

Data Index: 1402301 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4190. Min Act: -0.1700

Data Index: 3325536 (Open Web Text)

Max Activating Token Index: 578

Text #19

Max Range: 4.6726. Min Range: -4.6726

Max Act: 4.4250. Min Act: -0.1700

Data Index: 4953215 (Open Web Text)

Max Activating Token Index: 98