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

Dataset: Open Web Text

Neuron 2463 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: 1.4437. Min Range: -1.4437

Max Act: 1.4437. Min Act: -0.1700

Data Index: 4879622 (Open Web Text)

Max Activating Token Index: 786

Text #1

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.4274. Min Act: -0.1700

Data Index: 2783628 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.4111. Min Act: -0.1700

Data Index: 6613019 (Open Web Text)

Max Activating Token Index: 955

Text #3

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3969. Min Act: -0.1700

Data Index: 463209 (Open Web Text)

Max Activating Token Index: 108

Text #4

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3908. Min Act: -0.1700

Data Index: 6368924 (Open Web Text)

Max Activating Token Index: 559

Text #5

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3849. Min Act: -0.1700

Data Index: 4322446 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3735. Min Act: -0.1700

Data Index: 1499669 (Open Web Text)

Max Activating Token Index: 299

Text #7

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3687. Min Act: -0.1699

Data Index: 755287 (Open Web Text)

Max Activating Token Index: 455

Text #8

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3656. Min Act: -0.1700

Data Index: 8583422 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3497. Min Act: -0.1700

Data Index: 1382989 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3547. Min Act: -0.1700

Data Index: 3715738 (Open Web Text)

Max Activating Token Index: 880

Text #11

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3518. Min Act: -0.1700

Data Index: 1641610 (Open Web Text)

Max Activating Token Index: 130

Text #12

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3451. Min Act: -0.1700

Data Index: 5275004 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3491. Min Act: -0.1699

Data Index: 1068678 (Open Web Text)

Max Activating Token Index: 978

Text #14

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3496. Min Act: -0.1699

Data Index: 8449467 (Open Web Text)

Max Activating Token Index: 873

Text #15

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3601. Min Act: -0.1700

Data Index: 2043455 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3464. Min Act: -0.1700

Data Index: 6109518 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3420. Min Act: -0.1700

Data Index: 5734241 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3410. Min Act: -0.1700

Data Index: 7017426 (Open Web Text)

Max Activating Token Index: 411

Text #19

Max Range: 1.4437. Min Range: -1.4437

Max Act: 1.3470. Min Act: -0.1699

Data Index: 8315492 (Open Web Text)

Max Activating Token Index: 992