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

Dataset: Open Web Text

Neuron 1873 in Layer 5

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: 4.6463. Min Range: -4.6463

Max Act: 4.6463. Min Act: -0.1700

Data Index: 5313600 (Open Web Text)

Max Activating Token Index: 316

Text #1

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.5669. Min Act: -0.1700

Data Index: 8298994 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.5626. Min Act: -0.1700

Data Index: 7309087 (Open Web Text)

Max Activating Token Index: 682

Text #3

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.5026. Min Act: -0.1700

Data Index: 3871044 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.5211. Min Act: -0.1700

Data Index: 6584855 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.4675. Min Act: -0.1700

Data Index: 6055519 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.4127. Min Act: -0.1700

Data Index: 2619737 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.4254. Min Act: -0.1700

Data Index: 6752930 (Open Web Text)

Max Activating Token Index: 154

Text #8

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.4650. Min Act: -0.1700

Data Index: 3265671 (Open Web Text)

Max Activating Token Index: 411

Text #9

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.4056. Min Act: -0.1700

Data Index: 5207600 (Open Web Text)

Max Activating Token Index: 507

Text #10

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3907. Min Act: -0.1700

Data Index: 4470360 (Open Web Text)

Max Activating Token Index: 593

Text #11

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3924. Min Act: -0.1700

Data Index: 1613114 (Open Web Text)

Max Activating Token Index: 813

Text #12

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3261. Min Act: -0.1700

Data Index: 8414723 (Open Web Text)

Max Activating Token Index: 595

Text #13

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3613. Min Act: -0.1700

Data Index: 3042899 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3217. Min Act: -0.1700

Data Index: 4017131 (Open Web Text)

Max Activating Token Index: 850

Text #15

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3560. Min Act: -0.1700

Data Index: 6591632 (Open Web Text)

Max Activating Token Index: 877

Text #16

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3107. Min Act: -0.1700

Data Index: 8767933 (Open Web Text)

Max Activating Token Index: 913

Text #17

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3213. Min Act: -0.1700

Data Index: 326802 (Open Web Text)

Max Activating Token Index: 674

Text #18

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3225. Min Act: -0.1700

Data Index: 3596954 (Open Web Text)

Max Activating Token Index: 216

Text #19

Max Range: 4.6463. Min Range: -4.6463

Max Act: 4.3174. Min Act: -0.1700

Data Index: 3063647 (Open Web Text)

Max Activating Token Index: 586