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

Dataset: Open Web Text

Neuron 1806 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: 3.8276. Min Range: -3.8276

Max Act: 3.8276. Min Act: -0.1700

Data Index: 1857707 (Open Web Text)

Max Activating Token Index: 929

Text #1

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.8164. Min Act: -0.1700

Data Index: 5002447 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7438. Min Act: -0.1700

Data Index: 4912593 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.7219. Min Act: -0.1700

Data Index: 3446742 (Open Web Text)

Max Activating Token Index: 872

Text #4

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6212. Min Act: -0.1700

Data Index: 7799056 (Open Web Text)

Max Activating Token Index: 725

Text #5

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6428. Min Act: -0.1700

Data Index: 6127855 (Open Web Text)

Max Activating Token Index: 539

Text #6

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6354. Min Act: -0.1700

Data Index: 4990166 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5919. Min Act: -0.1700

Data Index: 3942296 (Open Web Text)

Max Activating Token Index: 284

Text #8

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.6159. Min Act: -0.1700

Data Index: 3596535 (Open Web Text)

Max Activating Token Index: 1004

Text #9

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5702. Min Act: -0.1700

Data Index: 4218247 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5833. Min Act: -0.1700

Data Index: 8120068 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5774. Min Act: -0.1700

Data Index: 5576864 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5596. Min Act: -0.1700

Data Index: 4025875 (Open Web Text)

Max Activating Token Index: 995

Text #13

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5664. Min Act: -0.1700

Data Index: 7945147 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5476. Min Act: -0.1700

Data Index: 8258583 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5676. Min Act: -0.1700

Data Index: 5758897 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5149. Min Act: -0.1700

Data Index: 3370134 (Open Web Text)

Max Activating Token Index: 533

Text #17

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5348. Min Act: -0.1700

Data Index: 5529871 (Open Web Text)

Max Activating Token Index: 340

Text #18

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5259. Min Act: -0.1700

Data Index: 6586909 (Open Web Text)

Max Activating Token Index: 200

Text #19

Max Range: 3.8276. Min Range: -3.8276

Max Act: 3.5362. Min Act: -0.1700

Data Index: 4432523 (Open Web Text)

Max Activating Token Index: 592