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

Dataset: Open Web Text

Neuron 2209 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: 1.3985. Min Range: -1.3985

Max Act: 1.3985. Min Act: -0.1533

Data Index: 6976429 (Open Web Text)

Max Activating Token Index: 1001

Text #1

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3908. Min Act: -0.1364

Data Index: 2055083 (Open Web Text)

Max Activating Token Index: 139

Text #2

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3737. Min Act: -0.1578

Data Index: 5196119 (Open Web Text)

Max Activating Token Index: 965

Text #3

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3610. Min Act: -0.1479

Data Index: 899384 (Open Web Text)

Max Activating Token Index: 512

Text #4

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3533. Min Act: -0.1232

Data Index: 6016219 (Open Web Text)

Max Activating Token Index: 399

Text #5

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3536. Min Act: -0.1655

Data Index: 8519308 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3299. Min Act: -0.1551

Data Index: 6957672 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3261. Min Act: -0.1532

Data Index: 8173351 (Open Web Text)

Max Activating Token Index: 423

Text #8

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3222. Min Act: -0.1600

Data Index: 1340510 (Open Web Text)

Max Activating Token Index: 643

Text #9

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3222. Min Act: -0.1638

Data Index: 8515841 (Open Web Text)

Max Activating Token Index: 781

Text #10

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3090. Min Act: -0.1509

Data Index: 8811455 (Open Web Text)

Max Activating Token Index: 245

Text #11

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3157. Min Act: -0.1486

Data Index: 1839183 (Open Web Text)

Max Activating Token Index: 941

Text #12

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3039. Min Act: -0.1607

Data Index: 8629193 (Open Web Text)

Max Activating Token Index: 137

Text #13

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3125. Min Act: -0.1576

Data Index: 4627423 (Open Web Text)

Max Activating Token Index: 760

Text #14

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2990. Min Act: -0.1429

Data Index: 7009881 (Open Web Text)

Max Activating Token Index: 459

Text #15

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2994. Min Act: -0.1580

Data Index: 376141 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3039. Min Act: -0.1456

Data Index: 2011804 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2964. Min Act: -0.1643

Data Index: 8515840 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.2954. Min Act: -0.1578

Data Index: 4846124 (Open Web Text)

Max Activating Token Index: 232

Text #19

Max Range: 1.3985. Min Range: -1.3985

Max Act: 1.3039. Min Act: -0.1675

Data Index: 8285132 (Open Web Text)

Max Activating Token Index: 364