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

Dataset: Open Web Text

Neuron 1356 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: 3.2034. Min Range: -3.2034

Max Act: 3.2034. Min Act: -0.1700

Data Index: 8559949 (Open Web Text)

Max Activating Token Index: 545

Text #1

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1627632 (Open Web Text)

Max Activating Token Index: 488

Text #2

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1589. Min Act: -0.1700

Data Index: 7407345 (Open Web Text)

Max Activating Token Index: 342

Text #3

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1440. Min Act: -0.1700

Data Index: 4871876 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1687. Min Act: -0.1700

Data Index: 3887359 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1686. Min Act: -0.1700

Data Index: 7247245 (Open Web Text)

Max Activating Token Index: 230

Text #6

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1585. Min Act: -0.1700

Data Index: 6459540 (Open Web Text)

Max Activating Token Index: 267

Text #7

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1411. Min Act: -0.1700

Data Index: 4295762 (Open Web Text)

Max Activating Token Index: 124

Text #8

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1961. Min Act: -0.1700

Data Index: 4009802 (Open Web Text)

Max Activating Token Index: 983

Text #9

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1302. Min Act: -0.1700

Data Index: 5586379 (Open Web Text)

Max Activating Token Index: 249

Text #10

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1240. Min Act: -0.1700

Data Index: 5295854 (Open Web Text)

Max Activating Token Index: 476

Text #11

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1123. Min Act: -0.1700

Data Index: 1062446 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1410. Min Act: -0.1700

Data Index: 5799698 (Open Web Text)

Max Activating Token Index: 482

Text #13

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1370. Min Act: -0.1700

Data Index: 8757787 (Open Web Text)

Max Activating Token Index: 818

Text #14

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1231. Min Act: -0.1700

Data Index: 8516578 (Open Web Text)

Max Activating Token Index: 269

Text #15

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1088. Min Act: -0.1700

Data Index: 7919322 (Open Web Text)

Max Activating Token Index: 843

Text #16

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1142. Min Act: -0.1700

Data Index: 7595968 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1142. Min Act: -0.1700

Data Index: 3636341 (Open Web Text)

Max Activating Token Index: 242

Text #18

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.1050. Min Act: -0.1700

Data Index: 4892789 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 3.2034. Min Range: -3.2034

Max Act: 3.0937. Min Act: -0.1700

Data Index: 5750744 (Open Web Text)

Max Activating Token Index: 992