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

Dataset: Open Web Text

Neuron 2385 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: 1.8572. Min Range: -1.8572

Max Act: 1.8572. Min Act: -0.1700

Data Index: 3762014 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7800. Min Act: -0.1700

Data Index: 702693 (Open Web Text)

Max Activating Token Index: 313

Text #2

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7422. Min Act: -0.1700

Data Index: 686403 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7548. Min Act: -0.1700

Data Index: 7844965 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7194. Min Act: -0.1700

Data Index: 326401 (Open Web Text)

Max Activating Token Index: 287

Text #5

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7281. Min Act: -0.1700

Data Index: 564529 (Open Web Text)

Max Activating Token Index: 231

Text #6

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7090. Min Act: -0.1700

Data Index: 8180644 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7133. Min Act: -0.1700

Data Index: 6843398 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7106. Min Act: -0.1700

Data Index: 5452567 (Open Web Text)

Max Activating Token Index: 241

Text #9

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7115. Min Act: -0.1700

Data Index: 4208844 (Open Web Text)

Max Activating Token Index: 284

Text #10

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6999. Min Act: -0.1700

Data Index: 7557184 (Open Web Text)

Max Activating Token Index: 259

Text #11

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7097. Min Act: -0.1700

Data Index: 1946701 (Open Web Text)

Max Activating Token Index: 307

Text #12

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6904. Min Act: -0.1700

Data Index: 6806450 (Open Web Text)

Max Activating Token Index: 260

Text #13

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.7034. Min Act: -0.1700

Data Index: 6681282 (Open Web Text)

Max Activating Token Index: 340

Text #14

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6909. Min Act: -0.1700

Data Index: 8308608 (Open Web Text)

Max Activating Token Index: 312

Text #15

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6947. Min Act: -0.1700

Data Index: 3762015 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6966. Min Act: -0.1700

Data Index: 7557195 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6882. Min Act: -0.1700

Data Index: 3644848 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6801. Min Act: -0.1700

Data Index: 3599284 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 1.8572. Min Range: -1.8572

Max Act: 1.6751. Min Act: -0.1700

Data Index: 1935315 (Open Web Text)

Max Activating Token Index: 260