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

Dataset: Open Web Text

Neuron 1316 in Layer 2

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: 1.6554. Min Range: -1.6554

Max Act: 1.6554. Min Act: -0.1700

Data Index: 3240479 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6308. Min Act: -0.1700

Data Index: 4307598 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6369. Min Act: -0.1700

Data Index: 3240482 (Open Web Text)

Max Activating Token Index: 864

Text #3

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6213. Min Act: -0.1700

Data Index: 5531535 (Open Web Text)

Max Activating Token Index: 96

Text #4

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6017. Min Act: -0.1700

Data Index: 6079883 (Open Web Text)

Max Activating Token Index: 399

Text #5

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6153. Min Act: -0.1699

Data Index: 6162281 (Open Web Text)

Max Activating Token Index: 295

Text #6

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6094. Min Act: -0.1700

Data Index: 7929775 (Open Web Text)

Max Activating Token Index: 301

Text #7

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6119. Min Act: -0.1700

Data Index: 3240477 (Open Web Text)

Max Activating Token Index: 853

Text #8

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6191. Min Act: -0.1700

Data Index: 3240480 (Open Web Text)

Max Activating Token Index: 288

Text #9

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6100. Min Act: -0.1700

Data Index: 5888771 (Open Web Text)

Max Activating Token Index: 681

Text #10

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6090. Min Act: -0.1700

Data Index: 8234991 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6069. Min Act: -0.1700

Data Index: 2373032 (Open Web Text)

Max Activating Token Index: 205

Text #12

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6120. Min Act: -0.1700

Data Index: 3240483 (Open Web Text)

Max Activating Token Index: 316

Text #13

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6045. Min Act: -0.1700

Data Index: 5667948 (Open Web Text)

Max Activating Token Index: 111

Text #14

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6080. Min Act: -0.1700

Data Index: 6936297 (Open Web Text)

Max Activating Token Index: 146

Text #15

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.5930. Min Act: -0.1700

Data Index: 6207465 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.6005. Min Act: -0.1700

Data Index: 4417896 (Open Web Text)

Max Activating Token Index: 965

Text #17

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.5810. Min Act: -0.1700

Data Index: 2377445 (Open Web Text)

Max Activating Token Index: 359

Text #18

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.5693. Min Act: -0.1698

Data Index: 5824245 (Open Web Text)

Max Activating Token Index: 874

Text #19

Max Range: 1.6554. Min Range: -1.6554

Max Act: 1.5699. Min Act: -0.1700

Data Index: 4845004 (Open Web Text)

Max Activating Token Index: 899