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

Dataset: Open Web Text

Neuron 2991 in Layer 4

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: 4.3956. Min Range: -4.3956

Max Act: 4.3956. Min Act: -0.1700

Data Index: 7825900 (Open Web Text)

Max Activating Token Index: 653

Text #1

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.3478. Min Act: -0.1700

Data Index: 4226197 (Open Web Text)

Max Activating Token Index: 175

Text #2

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.2654. Min Act: -0.1700

Data Index: 8679092 (Open Web Text)

Max Activating Token Index: 795

Text #3

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.2840. Min Act: -0.1700

Data Index: 2295155 (Open Web Text)

Max Activating Token Index: 832

Text #4

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.2359. Min Act: -0.1700

Data Index: 2486087 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.2226. Min Act: -0.1700

Data Index: 4533056 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1961. Min Act: -0.1700

Data Index: 2319259 (Open Web Text)

Max Activating Token Index: 73

Text #7

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.2410. Min Act: -0.1700

Data Index: 7776206 (Open Web Text)

Max Activating Token Index: 792

Text #8

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1545. Min Act: -0.1700

Data Index: 819348 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1767. Min Act: -0.1700

Data Index: 5748069 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.2089. Min Act: -0.1700

Data Index: 5560397 (Open Web Text)

Max Activating Token Index: 134

Text #11

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1696. Min Act: -0.1700

Data Index: 2480844 (Open Web Text)

Max Activating Token Index: 152

Text #12

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1853. Min Act: -0.1700

Data Index: 1392620 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1806. Min Act: -0.1700

Data Index: 7153517 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1580. Min Act: -0.1700

Data Index: 3938819 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1548. Min Act: -0.1700

Data Index: 1236550 (Open Web Text)

Max Activating Token Index: 234

Text #16

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1300. Min Act: -0.1700

Data Index: 5382380 (Open Web Text)

Max Activating Token Index: 271

Text #17

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1486. Min Act: -0.1700

Data Index: 5288089 (Open Web Text)

Max Activating Token Index: 920

Text #18

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1497. Min Act: -0.1700

Data Index: 4910371 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 4.3956. Min Range: -4.3956

Max Act: 4.1494. Min Act: -0.1700

Data Index: 6665824 (Open Web Text)

Max Activating Token Index: 66