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

Dataset: Open Web Text

Neuron 2572 in Layer 4

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: 3.1146. Min Range: -3.1146

Max Act: 3.1146. Min Act: -0.1700

Data Index: 4155664 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 3.1146. Min Range: -3.1146

Max Act: 3.0975. Min Act: -0.1700

Data Index: 4695314 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9810. Min Act: -0.1700

Data Index: 6186567 (Open Web Text)

Max Activating Token Index: 389

Text #3

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9429. Min Act: -0.1700

Data Index: 7806287 (Open Web Text)

Max Activating Token Index: 698

Text #4

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9381. Min Act: -0.1700

Data Index: 7791856 (Open Web Text)

Max Activating Token Index: 985

Text #5

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9332. Min Act: -0.1700

Data Index: 880783 (Open Web Text)

Max Activating Token Index: 336

Text #6

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9496. Min Act: -0.1700

Data Index: 7532792 (Open Web Text)

Max Activating Token Index: 731

Text #7

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9262. Min Act: -0.1700

Data Index: 111805 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9228. Min Act: -0.1700

Data Index: 7667937 (Open Web Text)

Max Activating Token Index: 460

Text #9

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9287. Min Act: -0.1700

Data Index: 4479814 (Open Web Text)

Max Activating Token Index: 153

Text #10

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9406. Min Act: -0.1700

Data Index: 2168570 (Open Web Text)

Max Activating Token Index: 220

Text #11

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9212. Min Act: -0.1700

Data Index: 6252807 (Open Web Text)

Max Activating Token Index: 57

Text #12

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9074. Min Act: -0.1700

Data Index: 6553928 (Open Web Text)

Max Activating Token Index: 796

Text #13

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.8935. Min Act: -0.1700

Data Index: 7849750 (Open Web Text)

Max Activating Token Index: 734

Text #14

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9061. Min Act: -0.1700

Data Index: 8760459 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9007. Min Act: -0.1700

Data Index: 6553930 (Open Web Text)

Max Activating Token Index: 461

Text #16

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9074. Min Act: -0.1700

Data Index: 2783856 (Open Web Text)

Max Activating Token Index: 464

Text #17

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9064. Min Act: -0.1700

Data Index: 4673685 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.8890. Min Act: -0.1700

Data Index: 4605708 (Open Web Text)

Max Activating Token Index: 531

Text #19

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.8805. Min Act: -0.1700

Data Index: 580818 (Open Web Text)

Max Activating Token Index: 847