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

Dataset: Open Web Text

Neuron 658 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: 2.6232. Min Range: -2.6232

Max Act: 2.6232. Min Act: -0.1700

Data Index: 3416040 (Open Web Text)

Max Activating Token Index: 180

Text #1

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.6216. Min Act: -0.1700

Data Index: 3995649 (Open Web Text)

Max Activating Token Index: 164

Text #2

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5733. Min Act: -0.1700

Data Index: 7860372 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5654. Min Act: -0.1700

Data Index: 1065192 (Open Web Text)

Max Activating Token Index: 895

Text #4

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5516. Min Act: -0.1700

Data Index: 1868615 (Open Web Text)

Max Activating Token Index: 882

Text #5

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5463. Min Act: -0.1700

Data Index: 3968278 (Open Web Text)

Max Activating Token Index: 548

Text #6

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5239. Min Act: -0.1700

Data Index: 7722435 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5374. Min Act: -0.1700

Data Index: 679135 (Open Web Text)

Max Activating Token Index: 1001

Text #8

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5174. Min Act: -0.1700

Data Index: 3102997 (Open Web Text)

Max Activating Token Index: 346

Text #9

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5228. Min Act: -0.1700

Data Index: 7595867 (Open Web Text)

Max Activating Token Index: 957

Text #10

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5411. Min Act: -0.1700

Data Index: 5290127 (Open Web Text)

Max Activating Token Index: 719

Text #11

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5170. Min Act: -0.1700

Data Index: 2035818 (Open Web Text)

Max Activating Token Index: 327

Text #12

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5039. Min Act: -0.1700

Data Index: 5741746 (Open Web Text)

Max Activating Token Index: 424

Text #13

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5129. Min Act: -0.1700

Data Index: 3482242 (Open Web Text)

Max Activating Token Index: 935

Text #14

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5103. Min Act: -0.1700

Data Index: 5145671 (Open Web Text)

Max Activating Token Index: 821

Text #15

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5013. Min Act: -0.1700

Data Index: 8365957 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5019. Min Act: -0.1700

Data Index: 531841 (Open Web Text)

Max Activating Token Index: 176

Text #17

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.4957. Min Act: -0.1700

Data Index: 3304296 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5106. Min Act: -0.1700

Data Index: 3629355 (Open Web Text)

Max Activating Token Index: 283

Text #19

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.4956. Min Act: -0.1700

Data Index: 4135576 (Open Web Text)

Max Activating Token Index: 686