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

Dataset: Open Web Text

Neuron 1070 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: 2.4138. Min Range: -2.4138

Max Act: 2.4138. Min Act: -0.1700

Data Index: 3126725 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.3123. Min Act: -0.1700

Data Index: 1192731 (Open Web Text)

Max Activating Token Index: 801

Text #2

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.2460. Min Act: -0.1700

Data Index: 1516825 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.2030. Min Act: -0.1700

Data Index: 1344244 (Open Web Text)

Max Activating Token Index: 132

Text #4

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1796. Min Act: -0.1700

Data Index: 1854276 (Open Web Text)

Max Activating Token Index: 53

Text #5

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1702. Min Act: -0.1700

Data Index: 7600141 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1497. Min Act: -0.1700

Data Index: 4651700 (Open Web Text)

Max Activating Token Index: 423

Text #7

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1522. Min Act: -0.1700

Data Index: 6842066 (Open Web Text)

Max Activating Token Index: 773

Text #8

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1399. Min Act: -0.1700

Data Index: 3221408 (Open Web Text)

Max Activating Token Index: 635

Text #9

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1519. Min Act: -0.1700

Data Index: 1933596 (Open Web Text)

Max Activating Token Index: 603

Text #10

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.0964. Min Act: -0.1700

Data Index: 5219273 (Open Web Text)

Max Activating Token Index: 871

Text #11

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1291. Min Act: -0.1700

Data Index: 303039 (Open Web Text)

Max Activating Token Index: 983

Text #12

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1050. Min Act: -0.1700

Data Index: 3368760 (Open Web Text)

Max Activating Token Index: 538

Text #13

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1133. Min Act: -0.1700

Data Index: 5506866 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.0544. Min Act: -0.1700

Data Index: 4309165 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1050. Min Act: -0.1700

Data Index: 4058593 (Open Web Text)

Max Activating Token Index: 632

Text #16

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.0513. Min Act: -0.1700

Data Index: 4354120 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1038. Min Act: -0.1700

Data Index: 1677154 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.1007. Min Act: -0.1700

Data Index: 6036664 (Open Web Text)

Max Activating Token Index: 523

Text #19

Max Range: 2.4138. Min Range: -2.4138

Max Act: 2.0794. Min Act: -0.1700

Data Index: 3916191 (Open Web Text)

Max Activating Token Index: 372