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

Dataset: Open Web Text

Neuron 2347 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: 1.4480. Min Range: -1.4480

Max Act: 1.4480. Min Act: -0.1700

Data Index: 7558366 (Open Web Text)

Max Activating Token Index: 902

Text #1

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.4356. Min Act: -0.1700

Data Index: 2729430 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.4050. Min Act: -0.1695

Data Index: 4587809 (Open Web Text)

Max Activating Token Index: 162

Text #3

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3829. Min Act: -0.1700

Data Index: 1566765 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3741. Min Act: -0.1700

Data Index: 6113362 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3710. Min Act: -0.1700

Data Index: 5728345 (Open Web Text)

Max Activating Token Index: 304

Text #6

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3677. Min Act: -0.1700

Data Index: 7205669 (Open Web Text)

Max Activating Token Index: 638

Text #7

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3626. Min Act: -0.1700

Data Index: 1735900 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3582. Min Act: -0.1700

Data Index: 5152398 (Open Web Text)

Max Activating Token Index: 409

Text #9

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3566. Min Act: -0.1698

Data Index: 7216299 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3534. Min Act: -0.1700

Data Index: 1159875 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3584. Min Act: -0.1700

Data Index: 6654701 (Open Web Text)

Max Activating Token Index: 670

Text #12

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3569. Min Act: -0.1700

Data Index: 268374 (Open Web Text)

Max Activating Token Index: 955

Text #13

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3462. Min Act: -0.1700

Data Index: 8609613 (Open Web Text)

Max Activating Token Index: 738

Text #14

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3523. Min Act: -0.1700

Data Index: 1077127 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3495. Min Act: -0.1698

Data Index: 2562090 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3600. Min Act: -0.1641

Data Index: 4587819 (Open Web Text)

Max Activating Token Index: 821

Text #17

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3547. Min Act: -0.1700

Data Index: 1704835 (Open Web Text)

Max Activating Token Index: 62

Text #18

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3476. Min Act: -0.1700

Data Index: 2079488 (Open Web Text)

Max Activating Token Index: 339

Text #19

Max Range: 1.4480. Min Range: -1.4480

Max Act: 1.3443. Min Act: -0.1700

Data Index: 357222 (Open Web Text)

Max Activating Token Index: 838