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

Dataset: Open Web Text

Neuron 2175 in Layer 1

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: 3.2757. Min Range: -3.2757

Max Act: 3.2757. Min Act: -0.1700

Data Index: 1432393 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.2757. Min Range: -3.2757

Max Act: 3.2658. Min Act: -0.1700

Data Index: 706616 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.2757. Min Range: -3.2757

Max Act: 3.1070. Min Act: -0.1700

Data Index: 192083 (Open Web Text)

Max Activating Token Index: 589

Text #3

Max Range: 3.2757. Min Range: -3.2757

Max Act: 3.0161. Min Act: -0.1700

Data Index: 1221371 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9996. Min Act: -0.1700

Data Index: 4546922 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9713. Min Act: -0.1700

Data Index: 3019130 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9613. Min Act: -0.1700

Data Index: 3374515 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9564. Min Act: -0.1700

Data Index: 5904624 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9374. Min Act: -0.1700

Data Index: 4747677 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9156. Min Act: -0.1700

Data Index: 1764741 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9153. Min Act: -0.1700

Data Index: 1359339 (Open Web Text)

Max Activating Token Index: 340

Text #11

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.8875. Min Act: -0.1700

Data Index: 7661264 (Open Web Text)

Max Activating Token Index: 605

Text #12

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.8953. Min Act: -0.1700

Data Index: 397382 (Open Web Text)

Max Activating Token Index: 587

Text #13

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9135. Min Act: -0.1700

Data Index: 248060 (Open Web Text)

Max Activating Token Index: 188

Text #14

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9130. Min Act: -0.1700

Data Index: 4784574 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9012. Min Act: -0.1700

Data Index: 6345257 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9039. Min Act: -0.1700

Data Index: 2574286 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.8930. Min Act: -0.1700

Data Index: 1816235 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.9158. Min Act: -0.1700

Data Index: 2466119 (Open Web Text)

Max Activating Token Index: 289

Text #19

Max Range: 3.2757. Min Range: -3.2757

Max Act: 2.8897. Min Act: -0.1700

Data Index: 6100064 (Open Web Text)

Max Activating Token Index: 327