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

Dataset: Open Web Text

Neuron 1875 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: 3.1418. Min Range: -3.1418

Max Act: 3.1418. Min Act: -0.1700

Data Index: 1022981 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.1147. Min Act: -0.1700

Data Index: 4942640 (Open Web Text)

Max Activating Token Index: 223

Text #2

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0736. Min Act: -0.1700

Data Index: 1324220 (Open Web Text)

Max Activating Token Index: 916

Text #3

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0718. Min Act: -0.1700

Data Index: 4969554 (Open Web Text)

Max Activating Token Index: 901

Text #4

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0422. Min Act: -0.1700

Data Index: 4397186 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0195. Min Act: -0.1700

Data Index: 944628 (Open Web Text)

Max Activating Token Index: 956

Text #6

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0226. Min Act: -0.1700

Data Index: 2972293 (Open Web Text)

Max Activating Token Index: 141

Text #7

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0182. Min Act: -0.1700

Data Index: 7331908 (Open Web Text)

Max Activating Token Index: 477

Text #8

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0304. Min Act: -0.1700

Data Index: 7570591 (Open Web Text)

Max Activating Token Index: 915

Text #9

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0186. Min Act: -0.1700

Data Index: 695801 (Open Web Text)

Max Activating Token Index: 985

Text #10

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0340. Min Act: -0.1700

Data Index: 135829 (Open Web Text)

Max Activating Token Index: 704

Text #11

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0137. Min Act: -0.1700

Data Index: 8736059 (Open Web Text)

Max Activating Token Index: 206

Text #12

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0110. Min Act: -0.1700

Data Index: 8356261 (Open Web Text)

Max Activating Token Index: 218

Text #13

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0197. Min Act: -0.1700

Data Index: 3563452 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0206. Min Act: -0.1700

Data Index: 8043833 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 3.1418. Min Range: -3.1418

Max Act: 3.0021. Min Act: -0.1700

Data Index: 593730 (Open Web Text)

Max Activating Token Index: 960

Text #16

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9832. Min Act: -0.1700

Data Index: 8398307 (Open Web Text)

Max Activating Token Index: 859

Text #17

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9782. Min Act: -0.1700

Data Index: 4651425 (Open Web Text)

Max Activating Token Index: 620

Text #18

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9891. Min Act: -0.1700

Data Index: 379329 (Open Web Text)

Max Activating Token Index: 250

Text #19

Max Range: 3.1418. Min Range: -3.1418

Max Act: 2.9614. Min Act: -0.1700

Data Index: 6874873 (Open Web Text)

Max Activating Token Index: 599