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

Dataset: Open Web Text

Neuron 2287 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: 4.4221. Min Range: -4.4221

Max Act: 4.4221. Min Act: -0.1700

Data Index: 3174641 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3944. Min Act: -0.1700

Data Index: 4948001 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.4048. Min Act: -0.1700

Data Index: 7504971 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3756. Min Act: -0.1700

Data Index: 894307 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3629. Min Act: -0.1700

Data Index: 3979994 (Open Web Text)

Max Activating Token Index: 709

Text #5

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3575. Min Act: -0.1700

Data Index: 6305648 (Open Web Text)

Max Activating Token Index: 829

Text #6

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2870. Min Act: -0.1700

Data Index: 8428127 (Open Web Text)

Max Activating Token Index: 780

Text #7

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2670. Min Act: -0.1700

Data Index: 7196886 (Open Web Text)

Max Activating Token Index: 671

Text #8

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2620. Min Act: -0.1700

Data Index: 3671985 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2692. Min Act: -0.1700

Data Index: 1827644 (Open Web Text)

Max Activating Token Index: 467

Text #10

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2494. Min Act: -0.1700

Data Index: 8019077 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2129. Min Act: -0.1700

Data Index: 3270679 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2326. Min Act: -0.1700

Data Index: 6312707 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1834. Min Act: -0.1700

Data Index: 5873335 (Open Web Text)

Max Activating Token Index: 323

Text #14

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1823. Min Act: -0.1700

Data Index: 3814294 (Open Web Text)

Max Activating Token Index: 882

Text #15

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1618. Min Act: -0.1700

Data Index: 1094355 (Open Web Text)

Max Activating Token Index: 765

Text #16

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1982. Min Act: -0.1700

Data Index: 4122077 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1788. Min Act: -0.1700

Data Index: 2003217 (Open Web Text)

Max Activating Token Index: 107

Text #18

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1454. Min Act: -0.1700

Data Index: 1410532 (Open Web Text)

Max Activating Token Index: 372

Text #19

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1331. Min Act: -0.1700

Data Index: 2840811 (Open Web Text)

Max Activating Token Index: 377