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

Dataset: Open Web Text

Neuron 1746 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: 3.2364. Min Range: -3.2364

Max Act: 3.2364. Min Act: -0.1700

Data Index: 7212365 (Open Web Text)

Max Activating Token Index: 784

Text #1

Max Range: 3.2364. Min Range: -3.2364

Max Act: 3.1310. Min Act: -0.1700

Data Index: 4833625 (Open Web Text)

Max Activating Token Index: 250

Text #2

Max Range: 3.2364. Min Range: -3.2364

Max Act: 3.0735. Min Act: -0.1700

Data Index: 6643342 (Open Web Text)

Max Activating Token Index: 97

Text #3

Max Range: 3.2364. Min Range: -3.2364

Max Act: 3.0793. Min Act: -0.1700

Data Index: 4572738 (Open Web Text)

Max Activating Token Index: 782

Text #4

Max Range: 3.2364. Min Range: -3.2364

Max Act: 3.0388. Min Act: -0.1700

Data Index: 6094164 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 3.2364. Min Range: -3.2364

Max Act: 3.0359. Min Act: -0.1700

Data Index: 3677954 (Open Web Text)

Max Activating Token Index: 775

Text #6

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9873. Min Act: -0.1700

Data Index: 3551841 (Open Web Text)

Max Activating Token Index: 336

Text #7

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9680. Min Act: -0.1700

Data Index: 3908615 (Open Web Text)

Max Activating Token Index: 320

Text #8

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9514. Min Act: -0.1700

Data Index: 7556819 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9766. Min Act: -0.1700

Data Index: 6989405 (Open Web Text)

Max Activating Token Index: 667

Text #10

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9558. Min Act: -0.1700

Data Index: 3671436 (Open Web Text)

Max Activating Token Index: 785

Text #11

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9497. Min Act: -0.1700

Data Index: 5472199 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9495. Min Act: -0.1700

Data Index: 3337734 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9352. Min Act: -0.1700

Data Index: 1333603 (Open Web Text)

Max Activating Token Index: 771

Text #14

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9330. Min Act: -0.1700

Data Index: 8721036 (Open Web Text)

Max Activating Token Index: 65

Text #15

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9184. Min Act: -0.1700

Data Index: 3298022 (Open Web Text)

Max Activating Token Index: 758

Text #16

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9483. Min Act: -0.1700

Data Index: 2699949 (Open Web Text)

Max Activating Token Index: 495

Text #17

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.8968. Min Act: -0.1700

Data Index: 3539312 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.8963. Min Act: -0.1700

Data Index: 6095014 (Open Web Text)

Max Activating Token Index: 838

Text #19

Max Range: 3.2364. Min Range: -3.2364

Max Act: 2.9144. Min Act: -0.1700

Data Index: 6529061 (Open Web Text)

Max Activating Token Index: 495