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

Dataset: Open Web Text

Neuron 2373 in Layer 1

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: 0.7112. Min Range: -0.7112

Max Act: 0.7112. Min Act: -0.1699

Data Index: 6066989 (Open Web Text)

Max Activating Token Index: 228

Text #1

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6706. Min Act: -0.1700

Data Index: 2333896 (Open Web Text)

Max Activating Token Index: 231

Text #2

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6586. Min Act: -0.1700

Data Index: 6066990 (Open Web Text)

Max Activating Token Index: 231

Text #3

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6507. Min Act: -0.1700

Data Index: 6047432 (Open Web Text)

Max Activating Token Index: 227

Text #4

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6495. Min Act: -0.1699

Data Index: 6066988 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6339. Min Act: -0.1700

Data Index: 5245958 (Open Web Text)

Max Activating Token Index: 810

Text #6

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6284. Min Act: -0.1699

Data Index: 5026120 (Open Web Text)

Max Activating Token Index: 231

Text #7

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6272. Min Act: -0.1699

Data Index: 5602169 (Open Web Text)

Max Activating Token Index: 205

Text #8

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6199. Min Act: -0.1700

Data Index: 5783931 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6234. Min Act: -0.1700

Data Index: 1053506 (Open Web Text)

Max Activating Token Index: 301

Text #10

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6115. Min Act: -0.1699

Data Index: 7037872 (Open Web Text)

Max Activating Token Index: 222

Text #11

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6203. Min Act: -0.1699

Data Index: 7123591 (Open Web Text)

Max Activating Token Index: 214

Text #12

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6086. Min Act: -0.1700

Data Index: 7338067 (Open Web Text)

Max Activating Token Index: 795

Text #13

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6079. Min Act: -0.1700

Data Index: 7959183 (Open Web Text)

Max Activating Token Index: 222

Text #14

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6062. Min Act: -0.1700

Data Index: 7985427 (Open Web Text)

Max Activating Token Index: 250

Text #15

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6028. Min Act: -0.1700

Data Index: 8026529 (Open Web Text)

Max Activating Token Index: 254

Text #16

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6005. Min Act: -0.1700

Data Index: 8162051 (Open Web Text)

Max Activating Token Index: 870

Text #17

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5961. Min Act: -0.1700

Data Index: 22 (Open Web Text)

Max Activating Token Index: 0

Text #18

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5961. Min Act: -0.1699

Data Index: 20 (Open Web Text)

Max Activating Token Index: 0

Text #19

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5961. Min Act: -0.1700

Data Index: 21 (Open Web Text)

Max Activating Token Index: 0