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

Dataset: Open Web Text

Neuron 1851 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: 4.6325. Min Range: -4.6325

Max Act: 4.6325. Min Act: -0.1700

Data Index: 8348831 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.4133. Min Act: -0.1700

Data Index: 8234791 (Open Web Text)

Max Activating Token Index: 889

Text #2

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.4269. Min Act: -0.1700

Data Index: 6318016 (Open Web Text)

Max Activating Token Index: 866

Text #3

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.4013. Min Act: -0.1700

Data Index: 8437543 (Open Web Text)

Max Activating Token Index: 897

Text #4

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.4172. Min Act: -0.1700

Data Index: 462066 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.4200. Min Act: -0.1700

Data Index: 943577 (Open Web Text)

Max Activating Token Index: 425

Text #6

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3480. Min Act: -0.1700

Data Index: 5847597 (Open Web Text)

Max Activating Token Index: 789

Text #7

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3684. Min Act: -0.1700

Data Index: 7508202 (Open Web Text)

Max Activating Token Index: 783

Text #8

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3609. Min Act: -0.1700

Data Index: 1305875 (Open Web Text)

Max Activating Token Index: 875

Text #9

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3747. Min Act: -0.1700

Data Index: 7265095 (Open Web Text)

Max Activating Token Index: 380

Text #10

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3674. Min Act: -0.1700

Data Index: 4810654 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3904. Min Act: -0.1700

Data Index: 159470 (Open Web Text)

Max Activating Token Index: 318

Text #12

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3662. Min Act: -0.1700

Data Index: 8480832 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3515. Min Act: -0.1700

Data Index: 6593191 (Open Web Text)

Max Activating Token Index: 72

Text #14

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3591. Min Act: -0.1700

Data Index: 2047693 (Open Web Text)

Max Activating Token Index: 400

Text #15

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3615. Min Act: -0.1700

Data Index: 4708922 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3431. Min Act: -0.1700

Data Index: 220077 (Open Web Text)

Max Activating Token Index: 276

Text #17

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3177. Min Act: -0.1700

Data Index: 1277561 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3214. Min Act: -0.1700

Data Index: 4880298 (Open Web Text)

Max Activating Token Index: 267

Text #19

Max Range: 4.6325. Min Range: -4.6325

Max Act: 4.3067. Min Act: -0.1700

Data Index: 4676011 (Open Web Text)

Max Activating Token Index: 604