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

Dataset: Open Web Text

Neuron 2886 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: 3.8350. Min Range: -3.8350

Max Act: 3.8350. Min Act: -0.1700

Data Index: 5230224 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8307. Min Act: -0.1700

Data Index: 2238285 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8108. Min Act: -0.1700

Data Index: 6360661 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8239. Min Act: -0.1700

Data Index: 8319064 (Open Web Text)

Max Activating Token Index: 139

Text #4

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8171. Min Act: -0.1700

Data Index: 8472393 (Open Web Text)

Max Activating Token Index: 565

Text #5

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8152. Min Act: -0.1700

Data Index: 8758288 (Open Web Text)

Max Activating Token Index: 309

Text #6

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8327. Min Act: -0.1700

Data Index: 629082 (Open Web Text)

Max Activating Token Index: 584

Text #7

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7981. Min Act: -0.1700

Data Index: 3709453 (Open Web Text)

Max Activating Token Index: 344

Text #8

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7908. Min Act: -0.1700

Data Index: 1049633 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8045. Min Act: -0.1700

Data Index: 515532 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7907. Min Act: -0.1700

Data Index: 1442006 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8001. Min Act: -0.1700

Data Index: 3621020 (Open Web Text)

Max Activating Token Index: 130

Text #12

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7895. Min Act: -0.1700

Data Index: 3435983 (Open Web Text)

Max Activating Token Index: 187

Text #13

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7859. Min Act: -0.1700

Data Index: 3187015 (Open Web Text)

Max Activating Token Index: 451

Text #14

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7932. Min Act: -0.1700

Data Index: 3185565 (Open Web Text)

Max Activating Token Index: 614

Text #15

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7845. Min Act: -0.1700

Data Index: 1635596 (Open Web Text)

Max Activating Token Index: 151

Text #16

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.8132. Min Act: -0.1700

Data Index: 1626447 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7890. Min Act: -0.1700

Data Index: 3146890 (Open Web Text)

Max Activating Token Index: 295

Text #18

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7898. Min Act: -0.1700

Data Index: 905727 (Open Web Text)

Max Activating Token Index: 991

Text #19

Max Range: 3.8350. Min Range: -3.8350

Max Act: 3.7798. Min Act: -0.1700

Data Index: 80000 (Open Web Text)

Max Activating Token Index: 111