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

Dataset: Open Web Text

Neuron 2273 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: 0.9956. Min Range: -0.9956

Max Act: 0.9956. Min Act: -0.1483

Data Index: 2726745 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9836. Min Act: -0.1579

Data Index: 5673955 (Open Web Text)

Max Activating Token Index: 123

Text #2

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9477. Min Act: -0.1468

Data Index: 1868786 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9527. Min Act: -0.1624

Data Index: 3513000 (Open Web Text)

Max Activating Token Index: 129

Text #4

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9490. Min Act: -0.1690

Data Index: 3565966 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9435. Min Act: -0.1502

Data Index: 758656 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9416. Min Act: -0.1464

Data Index: 3233333 (Open Web Text)

Max Activating Token Index: 143

Text #7

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9469. Min Act: -0.1642

Data Index: 850534 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9311. Min Act: -0.1465

Data Index: 8357314 (Open Web Text)

Max Activating Token Index: 106

Text #9

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9335. Min Act: -0.1422

Data Index: 5255118 (Open Web Text)

Max Activating Token Index: 161

Text #10

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9301. Min Act: -0.1448

Data Index: 5081211 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9398. Min Act: -0.1548

Data Index: 4288932 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9322. Min Act: -0.1421

Data Index: 1445851 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9316. Min Act: -0.1242

Data Index: 835184 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9381. Min Act: -0.1628

Data Index: 1769281 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9230. Min Act: -0.1694

Data Index: 2588884 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9228. Min Act: -0.1459

Data Index: 4130942 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9221. Min Act: -0.1650

Data Index: 1213481 (Open Web Text)

Max Activating Token Index: 115

Text #18

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9257. Min Act: -0.1372

Data Index: 3838106 (Open Web Text)

Max Activating Token Index: 72

Text #19

Max Range: 0.9956. Min Range: -0.9956

Max Act: 0.9185. Min Act: -0.1525

Data Index: 3445459 (Open Web Text)

Max Activating Token Index: 25