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

Dataset: Open Web Text

Neuron 1323 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: 3.4492. Min Range: -3.4492

Max Act: 3.4492. Min Act: -0.1700

Data Index: 671837 (Open Web Text)

Max Activating Token Index: 350

Text #1

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3560. Min Act: -0.1700

Data Index: 7199068 (Open Web Text)

Max Activating Token Index: 453

Text #2

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3824. Min Act: -0.1700

Data Index: 8815044 (Open Web Text)

Max Activating Token Index: 609

Text #3

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3644. Min Act: -0.1700

Data Index: 932594 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3352. Min Act: -0.1700

Data Index: 7226683 (Open Web Text)

Max Activating Token Index: 621

Text #5

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3306. Min Act: -0.1700

Data Index: 4342166 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3232. Min Act: -0.1700

Data Index: 930984 (Open Web Text)

Max Activating Token Index: 620

Text #7

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3404. Min Act: -0.1700

Data Index: 3813011 (Open Web Text)

Max Activating Token Index: 548

Text #8

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3178. Min Act: -0.1700

Data Index: 1294755 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3343. Min Act: -0.1700

Data Index: 1659312 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3153. Min Act: -0.1700

Data Index: 6098515 (Open Web Text)

Max Activating Token Index: 706

Text #11

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3110. Min Act: -0.1700

Data Index: 8710353 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3184. Min Act: -0.1700

Data Index: 7776574 (Open Web Text)

Max Activating Token Index: 850

Text #13

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3085. Min Act: -0.1700

Data Index: 2170001 (Open Web Text)

Max Activating Token Index: 267

Text #14

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.2961. Min Act: -0.1700

Data Index: 8007028 (Open Web Text)

Max Activating Token Index: 817

Text #15

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.3140. Min Act: -0.1700

Data Index: 1821043 (Open Web Text)

Max Activating Token Index: 740

Text #16

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.2868. Min Act: -0.1700

Data Index: 6076175 (Open Web Text)

Max Activating Token Index: 216

Text #17

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.2385. Min Act: -0.1700

Data Index: 8370304 (Open Web Text)

Max Activating Token Index: 997

Text #18

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.2965. Min Act: -0.1700

Data Index: 7651205 (Open Web Text)

Max Activating Token Index: 507

Text #19

Max Range: 3.4492. Min Range: -3.4492

Max Act: 3.2604. Min Act: -0.1700

Data Index: 7620438 (Open Web Text)

Max Activating Token Index: 317