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

Dataset: Open Web Text

Neuron 1235 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: 3.1954. Min Range: -3.1954

Max Act: 3.1954. Min Act: -0.1700

Data Index: 4766454 (Open Web Text)

Max Activating Token Index: 579

Text #1

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1193439 (Open Web Text)

Max Activating Token Index: 379

Text #2

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.1599. Min Act: -0.1700

Data Index: 5848229 (Open Web Text)

Max Activating Token Index: 683

Text #3

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.1335. Min Act: -0.1700

Data Index: 8557998 (Open Web Text)

Max Activating Token Index: 710

Text #4

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.1398. Min Act: -0.1700

Data Index: 5148273 (Open Web Text)

Max Activating Token Index: 957

Text #5

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.1029. Min Act: -0.1700

Data Index: 3441768 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.1074. Min Act: -0.1700

Data Index: 4191003 (Open Web Text)

Max Activating Token Index: 994

Text #7

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0818. Min Act: -0.1700

Data Index: 1026144 (Open Web Text)

Max Activating Token Index: 439

Text #8

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0687. Min Act: -0.1700

Data Index: 7966306 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0790. Min Act: -0.1700

Data Index: 2957392 (Open Web Text)

Max Activating Token Index: 333

Text #10

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0480. Min Act: -0.1700

Data Index: 6041914 (Open Web Text)

Max Activating Token Index: 854

Text #11

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0259. Min Act: -0.1700

Data Index: 62450 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0573. Min Act: -0.1700

Data Index: 4913586 (Open Web Text)

Max Activating Token Index: 230

Text #13

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0404. Min Act: -0.1700

Data Index: 7725871 (Open Web Text)

Max Activating Token Index: 434

Text #14

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0275. Min Act: -0.1700

Data Index: 2109314 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0092. Min Act: -0.1700

Data Index: 6315356 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0140. Min Act: -0.1700

Data Index: 198085 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0308. Min Act: -0.1700

Data Index: 5340232 (Open Web Text)

Max Activating Token Index: 597

Text #18

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0282. Min Act: -0.1700

Data Index: 1155306 (Open Web Text)

Max Activating Token Index: 321

Text #19

Max Range: 3.1954. Min Range: -3.1954

Max Act: 3.0154. Min Act: -0.1700

Data Index: 7555347 (Open Web Text)

Max Activating Token Index: 521