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

Dataset: Open Web Text

Neuron 1301 in Layer 3

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: 3.6541. Min Range: -3.6541

Max Act: 3.6541. Min Act: -0.1700

Data Index: 7864376 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5735. Min Act: -0.1700

Data Index: 5521112 (Open Web Text)

Max Activating Token Index: 153

Text #2

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5312. Min Act: -0.1700

Data Index: 5764963 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.5589. Min Act: -0.1700

Data Index: 1053651 (Open Web Text)

Max Activating Token Index: 751

Text #4

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.4958. Min Act: -0.1700

Data Index: 2503510 (Open Web Text)

Max Activating Token Index: 162

Text #5

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.4606. Min Act: -0.1700

Data Index: 3782762 (Open Web Text)

Max Activating Token Index: 760

Text #6

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.4270. Min Act: -0.1700

Data Index: 2877772 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.4279. Min Act: -0.1700

Data Index: 3751479 (Open Web Text)

Max Activating Token Index: 876

Text #8

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.3852. Min Act: -0.1700

Data Index: 8029059 (Open Web Text)

Max Activating Token Index: 781

Text #9

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.4050. Min Act: -0.1700

Data Index: 3570438 (Open Web Text)

Max Activating Token Index: 248

Text #10

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.4104. Min Act: -0.1700

Data Index: 5472702 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.3798. Min Act: -0.1700

Data Index: 6254775 (Open Web Text)

Max Activating Token Index: 229

Text #12

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.3693. Min Act: -0.1700

Data Index: 1699395 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.3605. Min Act: -0.1700

Data Index: 1583268 (Open Web Text)

Max Activating Token Index: 900

Text #14

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1927548 (Open Web Text)

Max Activating Token Index: 902

Text #15

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.4107. Min Act: -0.1700

Data Index: 4406261 (Open Web Text)

Max Activating Token Index: 783

Text #16

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.4197. Min Act: -0.1700

Data Index: 3655968 (Open Web Text)

Max Activating Token Index: 934

Text #17

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.3518. Min Act: -0.1700

Data Index: 2264364 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.3976. Min Act: -0.1700

Data Index: 4116905 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 3.6541. Min Range: -3.6541

Max Act: 3.3856. Min Act: -0.1700

Data Index: 3143750 (Open Web Text)

Max Activating Token Index: 168