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

Dataset: Open Web Text

Neuron 2486 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: 3.9652. Min Range: -3.9652

Max Act: 3.9652. Min Act: -0.1700

Data Index: 8241018 (Open Web Text)

Max Activating Token Index: 598

Text #1

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.9386. Min Act: -0.1700

Data Index: 8514885 (Open Web Text)

Max Activating Token Index: 436

Text #2

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.8036. Min Act: -0.1700

Data Index: 1303707 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6923. Min Act: -0.1700

Data Index: 1142063 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6931. Min Act: -0.1700

Data Index: 2135026 (Open Web Text)

Max Activating Token Index: 806

Text #5

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6890. Min Act: -0.1700

Data Index: 8672073 (Open Web Text)

Max Activating Token Index: 801

Text #6

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6957. Min Act: -0.1700

Data Index: 1201606 (Open Web Text)

Max Activating Token Index: 803

Text #7

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.7058. Min Act: -0.1700

Data Index: 3281349 (Open Web Text)

Max Activating Token Index: 184

Text #8

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6549. Min Act: -0.1700

Data Index: 548780 (Open Web Text)

Max Activating Token Index: 790

Text #9

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6734. Min Act: -0.1700

Data Index: 7258494 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6932. Min Act: -0.1700

Data Index: 1600393 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6452. Min Act: -0.1700

Data Index: 1014458 (Open Web Text)

Max Activating Token Index: 342

Text #12

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6552. Min Act: -0.1700

Data Index: 5237367 (Open Web Text)

Max Activating Token Index: 454

Text #13

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6381. Min Act: -0.1700

Data Index: 1018927 (Open Web Text)

Max Activating Token Index: 737

Text #14

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6297. Min Act: -0.1700

Data Index: 2894436 (Open Web Text)

Max Activating Token Index: 669

Text #15

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6279. Min Act: -0.1700

Data Index: 3113933 (Open Web Text)

Max Activating Token Index: 759

Text #16

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6279. Min Act: -0.1700

Data Index: 4475593 (Open Web Text)

Max Activating Token Index: 336

Text #17

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6129. Min Act: -0.1700

Data Index: 5144347 (Open Web Text)

Max Activating Token Index: 712

Text #18

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6194. Min Act: -0.1700

Data Index: 4908924 (Open Web Text)

Max Activating Token Index: 169

Text #19

Max Range: 3.9652. Min Range: -3.9652

Max Act: 3.6068. Min Act: -0.1700

Data Index: 3222727 (Open Web Text)

Max Activating Token Index: 913