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

Dataset: Open Web Text

Neuron 1675 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: 5.1940. Min Range: -5.1940

Max Act: 5.1940. Min Act: -0.1700

Data Index: 1938307 (Open Web Text)

Max Activating Token Index: 914

Text #1

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.1746. Min Act: -0.1700

Data Index: 495210 (Open Web Text)

Max Activating Token Index: 1004

Text #2

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0887. Min Act: -0.1700

Data Index: 4209459 (Open Web Text)

Max Activating Token Index: 885

Text #3

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0891. Min Act: -0.1700

Data Index: 6037152 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0127. Min Act: -0.1700

Data Index: 2355364 (Open Web Text)

Max Activating Token Index: 909

Text #5

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0329. Min Act: -0.1700

Data Index: 4641888 (Open Web Text)

Max Activating Token Index: 927

Text #6

Max Range: 5.1940. Min Range: -5.1940

Max Act: 5.0687. Min Act: -0.1700

Data Index: 1593731 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9951. Min Act: -0.1700

Data Index: 2213119 (Open Web Text)

Max Activating Token Index: 937

Text #8

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9542. Min Act: -0.1700

Data Index: 1299262 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9709. Min Act: -0.1700

Data Index: 373632 (Open Web Text)

Max Activating Token Index: 890

Text #10

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9519. Min Act: -0.1700

Data Index: 7312346 (Open Web Text)

Max Activating Token Index: 639

Text #11

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9593. Min Act: -0.1700

Data Index: 3561219 (Open Web Text)

Max Activating Token Index: 946

Text #12

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9614. Min Act: -0.1700

Data Index: 4858906 (Open Web Text)

Max Activating Token Index: 494

Text #13

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9456. Min Act: -0.1700

Data Index: 3583596 (Open Web Text)

Max Activating Token Index: 402

Text #14

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9228. Min Act: -0.1700

Data Index: 6223950 (Open Web Text)

Max Activating Token Index: 531

Text #15

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.8943. Min Act: -0.1700

Data Index: 6824141 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.8848. Min Act: -0.1700

Data Index: 5453193 (Open Web Text)

Max Activating Token Index: 267

Text #17

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.9205. Min Act: -0.1700

Data Index: 2158742 (Open Web Text)

Max Activating Token Index: 91

Text #18

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.8983. Min Act: -0.1700

Data Index: 3914975 (Open Web Text)

Max Activating Token Index: 708

Text #19

Max Range: 5.1940. Min Range: -5.1940

Max Act: 4.8715. Min Act: -0.1700

Data Index: 3703870 (Open Web Text)

Max Activating Token Index: 53