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

Dataset: Open Web Text

Neuron 1351 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: 4.6340. Min Range: -4.6340

Max Act: 4.6307. Min Act: -0.1700

Data Index: 7262710 (Open Web Text)

Max Activating Token Index: 652

Text #1

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.6340. Min Act: -0.1700

Data Index: 8562016 (Open Web Text)

Max Activating Token Index: 673

Text #2

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.6157. Min Act: -0.1700

Data Index: 90612 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.5755. Min Act: -0.1700

Data Index: 7951873 (Open Web Text)

Max Activating Token Index: 641

Text #4

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.6022. Min Act: -0.1700

Data Index: 3067336 (Open Web Text)

Max Activating Token Index: 384

Text #5

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.5775. Min Act: -0.1700

Data Index: 7414702 (Open Web Text)

Max Activating Token Index: 432

Text #6

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.5453. Min Act: -0.1700

Data Index: 322698 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4774. Min Act: -0.1700

Data Index: 7548548 (Open Web Text)

Max Activating Token Index: 644

Text #8

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.5407. Min Act: -0.1700

Data Index: 5307649 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4716. Min Act: -0.1700

Data Index: 4888746 (Open Web Text)

Max Activating Token Index: 898

Text #10

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4445. Min Act: -0.1700

Data Index: 5269876 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4968. Min Act: -0.1700

Data Index: 6410695 (Open Web Text)

Max Activating Token Index: 184

Text #12

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4185. Min Act: -0.1700

Data Index: 5851833 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4446. Min Act: -0.1700

Data Index: 4005633 (Open Web Text)

Max Activating Token Index: 139

Text #14

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.3823. Min Act: -0.1700

Data Index: 5572361 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.3842. Min Act: -0.1700

Data Index: 873572 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4550. Min Act: -0.1700

Data Index: 278468 (Open Web Text)

Max Activating Token Index: 584

Text #17

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4502. Min Act: -0.1700

Data Index: 5534634 (Open Web Text)

Max Activating Token Index: 236

Text #18

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4144. Min Act: -0.1700

Data Index: 5874123 (Open Web Text)

Max Activating Token Index: 687

Text #19

Max Range: 4.6340. Min Range: -4.6340

Max Act: 4.4709. Min Act: -0.1700

Data Index: 1056246 (Open Web Text)

Max Activating Token Index: 215