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

Dataset: Open Web Text

Neuron 1388 in Layer 3

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: 4.4599. Min Range: -4.4599

Max Act: 4.4599. Min Act: -0.1700

Data Index: 6175721 (Open Web Text)

Max Activating Token Index: 680

Text #1

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.4468. Min Act: -0.1700

Data Index: 1121357 (Open Web Text)

Max Activating Token Index: 571

Text #2

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.3994. Min Act: -0.1700

Data Index: 7382251 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.3842. Min Act: -0.1700

Data Index: 5285272 (Open Web Text)

Max Activating Token Index: 316

Text #4

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.3626. Min Act: -0.1700

Data Index: 6030238 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.3330. Min Act: -0.1700

Data Index: 1732546 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2896. Min Act: -0.1700

Data Index: 1003513 (Open Web Text)

Max Activating Token Index: 725

Text #7

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2690. Min Act: -0.1700

Data Index: 4801107 (Open Web Text)

Max Activating Token Index: 984

Text #8

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2925. Min Act: -0.1700

Data Index: 7026217 (Open Web Text)

Max Activating Token Index: 873

Text #9

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.3226. Min Act: -0.1700

Data Index: 6030239 (Open Web Text)

Max Activating Token Index: 78

Text #10

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.3008. Min Act: -0.1700

Data Index: 1069751 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.3094. Min Act: -0.1700

Data Index: 4680992 (Open Web Text)

Max Activating Token Index: 459

Text #12

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2731. Min Act: -0.1700

Data Index: 1423564 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2777. Min Act: -0.1700

Data Index: 973149 (Open Web Text)

Max Activating Token Index: 94

Text #14

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2696. Min Act: -0.1700

Data Index: 3022240 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2601. Min Act: -0.1700

Data Index: 1035956 (Open Web Text)

Max Activating Token Index: 691

Text #16

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2623. Min Act: -0.1700

Data Index: 6339651 (Open Web Text)

Max Activating Token Index: 638

Text #17

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2956. Min Act: -0.1700

Data Index: 3181747 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2802. Min Act: -0.1700

Data Index: 6561489 (Open Web Text)

Max Activating Token Index: 911

Text #19

Max Range: 4.4599. Min Range: -4.4599

Max Act: 4.2795. Min Act: -0.1700

Data Index: 7052076 (Open Web Text)

Max Activating Token Index: 4