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

Dataset: Open Web Text

Neuron 2156 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: 3.4401. Min Range: -3.4401

Max Act: 3.4207. Min Act: -0.1700

Data Index: 1194471 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.4401. Min Act: -0.1700

Data Index: 6015636 (Open Web Text)

Max Activating Token Index: 146

Text #2

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3825. Min Act: -0.1700

Data Index: 1226168 (Open Web Text)

Max Activating Token Index: 561

Text #3

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3740. Min Act: -0.1700

Data Index: 171740 (Open Web Text)

Max Activating Token Index: 553

Text #4

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3573. Min Act: -0.1700

Data Index: 5551375 (Open Web Text)

Max Activating Token Index: 818

Text #5

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3533. Min Act: -0.1700

Data Index: 1861910 (Open Web Text)

Max Activating Token Index: 62

Text #6

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3450. Min Act: -0.1700

Data Index: 8105423 (Open Web Text)

Max Activating Token Index: 961

Text #7

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3456. Min Act: -0.1700

Data Index: 457182 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3085. Min Act: -0.1700

Data Index: 854996 (Open Web Text)

Max Activating Token Index: 759

Text #9

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3061. Min Act: -0.1700

Data Index: 5110404 (Open Web Text)

Max Activating Token Index: 577

Text #10

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3149. Min Act: -0.1700

Data Index: 6103558 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3353. Min Act: -0.1700

Data Index: 2955347 (Open Web Text)

Max Activating Token Index: 342

Text #12

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3140. Min Act: -0.1700

Data Index: 8775458 (Open Web Text)

Max Activating Token Index: 570

Text #13

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.3197. Min Act: -0.1700

Data Index: 3321880 (Open Web Text)

Max Activating Token Index: 656

Text #14

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2906. Min Act: -0.1700

Data Index: 1260239 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2898. Min Act: -0.1700

Data Index: 5693884 (Open Web Text)

Max Activating Token Index: 899

Text #16

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2894. Min Act: -0.1700

Data Index: 8744596 (Open Web Text)

Max Activating Token Index: 998

Text #17

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2989. Min Act: -0.1700

Data Index: 5692321 (Open Web Text)

Max Activating Token Index: 1019

Text #18

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2920. Min Act: -0.1700

Data Index: 3117547 (Open Web Text)

Max Activating Token Index: 938

Text #19

Max Range: 3.4401. Min Range: -3.4401

Max Act: 3.2861. Min Act: -0.1700

Data Index: 6596455 (Open Web Text)

Max Activating Token Index: 727