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

Dataset: Open Web Text

Neuron 2828 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: 4.0297. Min Range: -4.0297

Max Act: 4.0297. Min Act: -0.1700

Data Index: 3585206 (Open Web Text)

Max Activating Token Index: 121

Text #1

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.9632. Min Act: -0.1700

Data Index: 8185874 (Open Web Text)

Max Activating Token Index: 838

Text #2

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.9570. Min Act: -0.1700

Data Index: 3229010 (Open Web Text)

Max Activating Token Index: 183

Text #3

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.8990. Min Act: -0.1700

Data Index: 659142 (Open Web Text)

Max Activating Token Index: 782

Text #4

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.8627. Min Act: -0.1700

Data Index: 5616207 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.8570. Min Act: -0.1700

Data Index: 6179520 (Open Web Text)

Max Activating Token Index: 136

Text #6

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.8527. Min Act: -0.1700

Data Index: 4570828 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.8841. Min Act: -0.1700

Data Index: 5202152 (Open Web Text)

Max Activating Token Index: 497

Text #8

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.8265. Min Act: -0.1700

Data Index: 6959481 (Open Web Text)

Max Activating Token Index: 75

Text #9

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7920. Min Act: -0.1700

Data Index: 5431084 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7971. Min Act: -0.1700

Data Index: 6909047 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.8152. Min Act: -0.1700

Data Index: 5232038 (Open Web Text)

Max Activating Token Index: 142

Text #12

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7859. Min Act: -0.1700

Data Index: 6278152 (Open Web Text)

Max Activating Token Index: 289

Text #13

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7969. Min Act: -0.1700

Data Index: 3960137 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7751. Min Act: -0.1700

Data Index: 1873225 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7917. Min Act: -0.1700

Data Index: 7428961 (Open Web Text)

Max Activating Token Index: 198

Text #16

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7434. Min Act: -0.1700

Data Index: 2067977 (Open Web Text)

Max Activating Token Index: 290

Text #17

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7599. Min Act: -0.1700

Data Index: 536100 (Open Web Text)

Max Activating Token Index: 345

Text #18

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7650. Min Act: -0.1700

Data Index: 2651036 (Open Web Text)

Max Activating Token Index: 507

Text #19

Max Range: 4.0297. Min Range: -4.0297

Max Act: 3.7769. Min Act: -0.1700

Data Index: 6894698 (Open Web Text)

Max Activating Token Index: 438