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

Dataset: Open Web Text

Neuron 600 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: 1.9510. Min Range: -1.9510

Max Act: 1.9510. Min Act: -0.1700

Data Index: 4369846 (Open Web Text)

Max Activating Token Index: 72

Text #1

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9422. Min Act: -0.1700

Data Index: 5346618 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9389. Min Act: -0.1700

Data Index: 3985006 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9457. Min Act: -0.1700

Data Index: 5893643 (Open Web Text)

Max Activating Token Index: 769

Text #4

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9270. Min Act: -0.1700

Data Index: 1481499 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9403. Min Act: -0.1700

Data Index: 7714624 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9401. Min Act: -0.1700

Data Index: 3899509 (Open Web Text)

Max Activating Token Index: 102

Text #7

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9241. Min Act: -0.1700

Data Index: 6789520 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9296. Min Act: -0.1700

Data Index: 1412378 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9438. Min Act: -0.1700

Data Index: 291782 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9277. Min Act: -0.1700

Data Index: 8120870 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9338. Min Act: -0.1700

Data Index: 5514316 (Open Web Text)

Max Activating Token Index: 719

Text #12

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9233. Min Act: -0.1700

Data Index: 4580996 (Open Web Text)

Max Activating Token Index: 226

Text #13

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9206. Min Act: -0.1699

Data Index: 4825404 (Open Web Text)

Max Activating Token Index: 449

Text #14

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9196. Min Act: -0.1700

Data Index: 406776 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9173. Min Act: -0.1700

Data Index: 8760820 (Open Web Text)

Max Activating Token Index: 811

Text #16

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.8999. Min Act: -0.1700

Data Index: 144267 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9033. Min Act: -0.1700

Data Index: 1173763 (Open Web Text)

Max Activating Token Index: 285

Text #18

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9001. Min Act: -0.1700

Data Index: 6950033 (Open Web Text)

Max Activating Token Index: 194

Text #19

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.8975. Min Act: -0.1700

Data Index: 7362059 (Open Web Text)

Max Activating Token Index: 854