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

Dataset: Open Web Text

Neuron 467 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: 4.5375. Min Range: -4.5375

Max Act: 4.5375. Min Act: -0.1700

Data Index: 7510396 (Open Web Text)

Max Activating Token Index: 538

Text #1

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.5373. Min Act: -0.1700

Data Index: 4218021 (Open Web Text)

Max Activating Token Index: 317

Text #2

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.5243. Min Act: -0.1700

Data Index: 230637 (Open Web Text)

Max Activating Token Index: 101

Text #3

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4969. Min Act: -0.1700

Data Index: 3293416 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4749. Min Act: -0.1700

Data Index: 1390393 (Open Web Text)

Max Activating Token Index: 535

Text #5

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4810. Min Act: -0.1700

Data Index: 7381471 (Open Web Text)

Max Activating Token Index: 549

Text #6

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4856. Min Act: -0.1700

Data Index: 7527063 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4706. Min Act: -0.1700

Data Index: 2844122 (Open Web Text)

Max Activating Token Index: 397

Text #8

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4554. Min Act: -0.1700

Data Index: 6090080 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4282. Min Act: -0.1700

Data Index: 5741438 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4417. Min Act: -0.1700

Data Index: 5419320 (Open Web Text)

Max Activating Token Index: 589

Text #11

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4613. Min Act: -0.1700

Data Index: 2177997 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4582. Min Act: -0.1700

Data Index: 8627427 (Open Web Text)

Max Activating Token Index: 280

Text #13

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4521. Min Act: -0.1700

Data Index: 7959099 (Open Web Text)

Max Activating Token Index: 146

Text #14

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4200. Min Act: -0.1700

Data Index: 4942632 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4396. Min Act: -0.1700

Data Index: 7527668 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4178. Min Act: -0.1700

Data Index: 7065855 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4276. Min Act: -0.1700

Data Index: 2960322 (Open Web Text)

Max Activating Token Index: 435

Text #18

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4209. Min Act: -0.1700

Data Index: 997634 (Open Web Text)

Max Activating Token Index: 170

Text #19

Max Range: 4.5375. Min Range: -4.5375

Max Act: 4.4198. Min Act: -0.1700

Data Index: 7932583 (Open Web Text)

Max Activating Token Index: 135