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

Dataset: Open Web Text

Neuron 2899 in Layer 4

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: 2.5062. Min Range: -2.5062

Max Act: 2.5062. Min Act: -0.1700

Data Index: 5936513 (Open Web Text)

Max Activating Token Index: 841

Text #1

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.4887. Min Act: -0.1700

Data Index: 6196516 (Open Web Text)

Max Activating Token Index: 984

Text #2

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.4783. Min Act: -0.1700

Data Index: 1062435 (Open Web Text)

Max Activating Token Index: 869

Text #3

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.4873. Min Act: -0.1700

Data Index: 2976401 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.4906. Min Act: -0.1700

Data Index: 4571163 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3729. Min Act: -0.1700

Data Index: 5726543 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3343. Min Act: -0.1700

Data Index: 8400611 (Open Web Text)

Max Activating Token Index: 682

Text #7

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3530. Min Act: -0.1700

Data Index: 2662413 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3399. Min Act: -0.1700

Data Index: 2246057 (Open Web Text)

Max Activating Token Index: 569

Text #9

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3291. Min Act: -0.1700

Data Index: 5508935 (Open Web Text)

Max Activating Token Index: 614

Text #10

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3097. Min Act: -0.1700

Data Index: 2239425 (Open Web Text)

Max Activating Token Index: 960

Text #11

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3038. Min Act: -0.1700

Data Index: 5049869 (Open Web Text)

Max Activating Token Index: 351

Text #12

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3184. Min Act: -0.1700

Data Index: 3705302 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.2980. Min Act: -0.1700

Data Index: 5711751 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.2990. Min Act: -0.1700

Data Index: 384715 (Open Web Text)

Max Activating Token Index: 373

Text #15

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.2975. Min Act: -0.1700

Data Index: 4323241 (Open Web Text)

Max Activating Token Index: 254

Text #16

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.3199. Min Act: -0.1700

Data Index: 3879638 (Open Web Text)

Max Activating Token Index: 159

Text #17

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.2901. Min Act: -0.1700

Data Index: 4999793 (Open Web Text)

Max Activating Token Index: 818

Text #18

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.2748. Min Act: -0.1700

Data Index: 439012 (Open Web Text)

Max Activating Token Index: 172

Text #19

Max Range: 2.5062. Min Range: -2.5062

Max Act: 2.2955. Min Act: -0.1700

Data Index: 3453541 (Open Web Text)

Max Activating Token Index: 784