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

Dataset: Open Web Text

Neuron 1260 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: 4.2934. Min Range: -4.2934

Max Act: 4.2934. Min Act: -0.1700

Data Index: 8027870 (Open Web Text)

Max Activating Token Index: 1000

Text #1

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.2248. Min Act: -0.1700

Data Index: 983706 (Open Web Text)

Max Activating Token Index: 198

Text #2

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.2175. Min Act: -0.1700

Data Index: 2734694 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1871. Min Act: -0.1700

Data Index: 3455563 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1497. Min Act: -0.1700

Data Index: 7277960 (Open Web Text)

Max Activating Token Index: 148

Text #5

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1690. Min Act: -0.1700

Data Index: 4097283 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1840. Min Act: -0.1700

Data Index: 6298901 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1357. Min Act: -0.1700

Data Index: 6331335 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1199. Min Act: -0.1700

Data Index: 1949592 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1675. Min Act: -0.1700

Data Index: 5677043 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1102. Min Act: -0.1700

Data Index: 8813374 (Open Web Text)

Max Activating Token Index: 823

Text #11

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.0698. Min Act: -0.1700

Data Index: 2162532 (Open Web Text)

Max Activating Token Index: 448

Text #12

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.0933. Min Act: -0.1700

Data Index: 3580229 (Open Web Text)

Max Activating Token Index: 466

Text #13

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1248. Min Act: -0.1700

Data Index: 8537849 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1141. Min Act: -0.1700

Data Index: 896191 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.1116. Min Act: -0.1700

Data Index: 3304248 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.0688. Min Act: -0.1700

Data Index: 7371514 (Open Web Text)

Max Activating Token Index: 491

Text #17

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.0849. Min Act: -0.1700

Data Index: 515056 (Open Web Text)

Max Activating Token Index: 418

Text #18

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.0820. Min Act: -0.1700

Data Index: 410428 (Open Web Text)

Max Activating Token Index: 172

Text #19

Max Range: 4.2934. Min Range: -4.2934

Max Act: 4.0978. Min Act: -0.1700

Data Index: 4172339 (Open Web Text)

Max Activating Token Index: 410