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

Dataset: Open Web Text

Neuron 184 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: 3.1210. Min Range: -3.1210

Max Act: 3.1210. Min Act: -0.1700

Data Index: 997786 (Open Web Text)

Max Activating Token Index: 367

Text #1

Max Range: 3.1210. Min Range: -3.1210

Max Act: 3.0490. Min Act: -0.1700

Data Index: 3504153 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 3.1210. Min Range: -3.1210

Max Act: 3.0458. Min Act: -0.1700

Data Index: 3097646 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 3.1210. Min Range: -3.1210

Max Act: 3.0718. Min Act: -0.1700

Data Index: 7169568 (Open Web Text)

Max Activating Token Index: 947

Text #4

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9895. Min Act: -0.1700

Data Index: 4018816 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9956. Min Act: -0.1700

Data Index: 3483419 (Open Web Text)

Max Activating Token Index: 955

Text #6

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9946. Min Act: -0.1700

Data Index: 8202862 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9852. Min Act: -0.1700

Data Index: 2370446 (Open Web Text)

Max Activating Token Index: 642

Text #8

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9964. Min Act: -0.1700

Data Index: 8421821 (Open Web Text)

Max Activating Token Index: 490

Text #9

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9663. Min Act: -0.1700

Data Index: 4498494 (Open Web Text)

Max Activating Token Index: 865

Text #10

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9702. Min Act: -0.1700

Data Index: 1366820 (Open Web Text)

Max Activating Token Index: 215

Text #11

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9631. Min Act: -0.1700

Data Index: 869703 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9819. Min Act: -0.1700

Data Index: 6804595 (Open Web Text)

Max Activating Token Index: 722

Text #13

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9254. Min Act: -0.1700

Data Index: 7737081 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9307. Min Act: -0.1700

Data Index: 3829452 (Open Web Text)

Max Activating Token Index: 119

Text #15

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9445. Min Act: -0.1700

Data Index: 6771538 (Open Web Text)

Max Activating Token Index: 651

Text #16

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9267. Min Act: -0.1700

Data Index: 2968837 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9363. Min Act: -0.1700

Data Index: 6690818 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9452. Min Act: -0.1700

Data Index: 4754089 (Open Web Text)

Max Activating Token Index: 462

Text #19

Max Range: 3.1210. Min Range: -3.1210

Max Act: 2.9281. Min Act: -0.1700

Data Index: 8400510 (Open Web Text)

Max Activating Token Index: 575