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

Dataset: Open Web Text

Neuron 2278 in Layer 2

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: 4.7350. Min Range: -4.7350

Max Act: 4.7350. Min Act: -0.1700

Data Index: 6096367 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.6420. Min Act: -0.1700

Data Index: 6846866 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.6292. Min Act: -0.1700

Data Index: 5441879 (Open Web Text)

Max Activating Token Index: 104

Text #3

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.6084. Min Act: -0.1700

Data Index: 5595145 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.5996. Min Act: -0.1700

Data Index: 1544696 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.5524. Min Act: -0.1700

Data Index: 3159410 (Open Web Text)

Max Activating Token Index: 698

Text #6

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.5436. Min Act: -0.1700

Data Index: 1919989 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.5552. Min Act: -0.1700

Data Index: 5808359 (Open Web Text)

Max Activating Token Index: 51

Text #8

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.5161. Min Act: -0.1700

Data Index: 6816308 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4859. Min Act: -0.1700

Data Index: 6631041 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4949. Min Act: -0.1700

Data Index: 4579146 (Open Web Text)

Max Activating Token Index: 635

Text #11

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4880. Min Act: -0.1700

Data Index: 4048476 (Open Web Text)

Max Activating Token Index: 531

Text #12

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4971. Min Act: -0.1700

Data Index: 1819958 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4921. Min Act: -0.1700

Data Index: 6428597 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.5128. Min Act: -0.1700

Data Index: 7994603 (Open Web Text)

Max Activating Token Index: 345

Text #15

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.5046. Min Act: -0.1700

Data Index: 6116614 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4768. Min Act: -0.1700

Data Index: 2481735 (Open Web Text)

Max Activating Token Index: 355

Text #17

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4890. Min Act: -0.1700

Data Index: 5786007 (Open Web Text)

Max Activating Token Index: 108

Text #18

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4923. Min Act: -0.1700

Data Index: 5230124 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 4.7350. Min Range: -4.7350

Max Act: 4.4696. Min Act: -0.1700

Data Index: 3917096 (Open Web Text)

Max Activating Token Index: 379