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

Dataset: Open Web Text

Neuron 430 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: 3.7750. Min Range: -3.7750

Max Act: 3.7750. Min Act: -0.1700

Data Index: 7184928 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.5784. Min Act: -0.1700

Data Index: 3136058 (Open Web Text)

Max Activating Token Index: 85

Text #2

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.5171. Min Act: -0.1700

Data Index: 2204093 (Open Web Text)

Max Activating Token Index: 399

Text #3

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4627. Min Act: -0.1700

Data Index: 722900 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4781. Min Act: -0.1700

Data Index: 1690336 (Open Web Text)

Max Activating Token Index: 413

Text #5

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4597. Min Act: -0.1700

Data Index: 6367790 (Open Web Text)

Max Activating Token Index: 805

Text #6

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4351. Min Act: -0.1700

Data Index: 4840407 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4034. Min Act: -0.1700

Data Index: 7455185 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4097. Min Act: -0.1700

Data Index: 4997556 (Open Web Text)

Max Activating Token Index: 246

Text #9

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.4264. Min Act: -0.1700

Data Index: 7399954 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3968. Min Act: -0.1700

Data Index: 2872440 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3517. Min Act: -0.1700

Data Index: 2180880 (Open Web Text)

Max Activating Token Index: 837

Text #12

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3279. Min Act: -0.1700

Data Index: 1594278 (Open Web Text)

Max Activating Token Index: 792

Text #13

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3381. Min Act: -0.1700

Data Index: 1639357 (Open Web Text)

Max Activating Token Index: 851

Text #14

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3260. Min Act: -0.1700

Data Index: 8103701 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3046. Min Act: -0.1700

Data Index: 8449755 (Open Web Text)

Max Activating Token Index: 278

Text #16

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3461. Min Act: -0.1700

Data Index: 208486 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3261. Min Act: -0.1700

Data Index: 5176905 (Open Web Text)

Max Activating Token Index: 355

Text #18

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.2952. Min Act: -0.1700

Data Index: 4277997 (Open Web Text)

Max Activating Token Index: 470

Text #19

Max Range: 3.7750. Min Range: -3.7750

Max Act: 3.3016. Min Act: -0.1700

Data Index: 4512050 (Open Web Text)

Max Activating Token Index: 300