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

Dataset: Open Web Text

Neuron 2187 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: 3.7154. Min Range: -3.7154

Max Act: 3.7154. Min Act: -0.1700

Data Index: 4272245 (Open Web Text)

Max Activating Token Index: 940

Text #1

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6800. Min Act: -0.1700

Data Index: 7564877 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6738. Min Act: -0.1700

Data Index: 8670953 (Open Web Text)

Max Activating Token Index: 442

Text #3

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6507. Min Act: -0.1700

Data Index: 2689467 (Open Web Text)

Max Activating Token Index: 883

Text #4

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6385. Min Act: -0.1700

Data Index: 7639830 (Open Web Text)

Max Activating Token Index: 691

Text #5

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6280. Min Act: -0.1700

Data Index: 4008075 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6221. Min Act: -0.1700

Data Index: 5948184 (Open Web Text)

Max Activating Token Index: 219

Text #7

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6065. Min Act: -0.1700

Data Index: 8027973 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6174. Min Act: -0.1700

Data Index: 8768060 (Open Web Text)

Max Activating Token Index: 79

Text #9

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5956. Min Act: -0.1700

Data Index: 7383577 (Open Web Text)

Max Activating Token Index: 694

Text #10

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.6125. Min Act: -0.1700

Data Index: 5327619 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5620. Min Act: -0.1700

Data Index: 3922042 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5716. Min Act: -0.1700

Data Index: 7809650 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5515. Min Act: -0.1700

Data Index: 2797446 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5681. Min Act: -0.1700

Data Index: 214195 (Open Web Text)

Max Activating Token Index: 866

Text #15

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5558. Min Act: -0.1700

Data Index: 2795004 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5437. Min Act: -0.1700

Data Index: 11628 (Open Web Text)

Max Activating Token Index: 948

Text #17

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5600. Min Act: -0.1700

Data Index: 1845463 (Open Web Text)

Max Activating Token Index: 115

Text #18

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5428. Min Act: -0.1700

Data Index: 6494555 (Open Web Text)

Max Activating Token Index: 82

Text #19

Max Range: 3.7154. Min Range: -3.7154

Max Act: 3.5717. Min Act: -0.1700

Data Index: 4523037 (Open Web Text)

Max Activating Token Index: 479