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

Dataset: Open Web Text

Neuron 305 in Layer 6

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: 3.8922. Min Range: -3.8922

Max Act: 3.8922. Min Act: -0.1700

Data Index: 6954383 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.7595. Min Act: -0.1700

Data Index: 1610969 (Open Web Text)

Max Activating Token Index: 369

Text #2

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.7608. Min Act: -0.1700

Data Index: 3347049 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.6140. Min Act: -0.1700

Data Index: 8454855 (Open Web Text)

Max Activating Token Index: 981

Text #4

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5675. Min Act: -0.1700

Data Index: 1136347 (Open Web Text)

Max Activating Token Index: 232

Text #5

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5623. Min Act: -0.1700

Data Index: 3745712 (Open Web Text)

Max Activating Token Index: 409

Text #6

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5726. Min Act: -0.1700

Data Index: 6174844 (Open Web Text)

Max Activating Token Index: 980

Text #7

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5450. Min Act: -0.1700

Data Index: 6966907 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5474. Min Act: -0.1700

Data Index: 4098122 (Open Web Text)

Max Activating Token Index: 965

Text #9

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5215. Min Act: -0.1700

Data Index: 2310502 (Open Web Text)

Max Activating Token Index: 531

Text #10

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5031. Min Act: -0.1700

Data Index: 2634676 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4921. Min Act: -0.1700

Data Index: 1967839 (Open Web Text)

Max Activating Token Index: 123

Text #12

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.5204. Min Act: -0.1700

Data Index: 6678986 (Open Web Text)

Max Activating Token Index: 619

Text #13

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4988. Min Act: -0.1700

Data Index: 7025940 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4922. Min Act: -0.1700

Data Index: 1942062 (Open Web Text)

Max Activating Token Index: 729

Text #15

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4678. Min Act: -0.1700

Data Index: 3701801 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4639. Min Act: -0.1700

Data Index: 8027666 (Open Web Text)

Max Activating Token Index: 801

Text #17

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4473. Min Act: -0.1700

Data Index: 1882109 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4486. Min Act: -0.1700

Data Index: 3362429 (Open Web Text)

Max Activating Token Index: 349

Text #19

Max Range: 3.8922. Min Range: -3.8922

Max Act: 3.4568. Min Act: -0.1700

Data Index: 2139284 (Open Web Text)

Max Activating Token Index: 676