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

Dataset: Open Web Text

Neuron 2222 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: 5.0453. Min Range: -5.0453

Max Act: 5.0453. Min Act: -0.1700

Data Index: 2155246 (Open Web Text)

Max Activating Token Index: 456

Text #1

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.9593. Min Act: -0.1700

Data Index: 2147416 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8976. Min Act: -0.1700

Data Index: 2371475 (Open Web Text)

Max Activating Token Index: 765

Text #3

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8858. Min Act: -0.1700

Data Index: 3024904 (Open Web Text)

Max Activating Token Index: 125

Text #4

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8973. Min Act: -0.1700

Data Index: 1915721 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8742. Min Act: -0.1700

Data Index: 5774524 (Open Web Text)

Max Activating Token Index: 204

Text #6

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8213. Min Act: -0.1700

Data Index: 8152198 (Open Web Text)

Max Activating Token Index: 395

Text #7

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8276. Min Act: -0.1700

Data Index: 1439952 (Open Web Text)

Max Activating Token Index: 444

Text #8

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8515. Min Act: -0.1700

Data Index: 8633756 (Open Web Text)

Max Activating Token Index: 456

Text #9

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8266. Min Act: -0.1700

Data Index: 1951487 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.8128. Min Act: -0.1700

Data Index: 1824350 (Open Web Text)

Max Activating Token Index: 601

Text #11

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.7786. Min Act: -0.1700

Data Index: 7978054 (Open Web Text)

Max Activating Token Index: 161

Text #12

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.7806. Min Act: -0.1700

Data Index: 3466488 (Open Web Text)

Max Activating Token Index: 544

Text #13

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.7500. Min Act: -0.1700

Data Index: 4237203 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.7496. Min Act: -0.1700

Data Index: 3888826 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.7336. Min Act: -0.1700

Data Index: 2940964 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.7692. Min Act: -0.1700

Data Index: 2319089 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.7696. Min Act: -0.1700

Data Index: 2359943 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.6932. Min Act: -0.1700

Data Index: 6946831 (Open Web Text)

Max Activating Token Index: 856

Text #19

Max Range: 5.0453. Min Range: -5.0453

Max Act: 4.7028. Min Act: -0.1700

Data Index: 3312550 (Open Web Text)

Max Activating Token Index: 864