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

Dataset: Open Web Text

Neuron 2354 in Layer 3

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: 4.3493. Min Range: -4.3493

Max Act: 4.3493. Min Act: -0.1700

Data Index: 3649958 (Open Web Text)

Max Activating Token Index: 964

Text #1

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1984. Min Act: -0.1700

Data Index: 2450126 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.2089. Min Act: -0.1700

Data Index: 3176120 (Open Web Text)

Max Activating Token Index: 825

Text #3

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.2174. Min Act: -0.1700

Data Index: 2575933 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.2124. Min Act: -0.1700

Data Index: 2450128 (Open Web Text)

Max Activating Token Index: 485

Text #5

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1609. Min Act: -0.1700

Data Index: 514225 (Open Web Text)

Max Activating Token Index: 962

Text #6

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1428. Min Act: -0.1700

Data Index: 1582459 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1303. Min Act: -0.1700

Data Index: 4548509 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1009. Min Act: -0.1700

Data Index: 7520408 (Open Web Text)

Max Activating Token Index: 44

Text #9

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1068. Min Act: -0.1700

Data Index: 2072831 (Open Web Text)

Max Activating Token Index: 883

Text #10

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1008. Min Act: -0.1700

Data Index: 8597810 (Open Web Text)

Max Activating Token Index: 503

Text #11

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1671. Min Act: -0.1700

Data Index: 2450127 (Open Web Text)

Max Activating Token Index: 567

Text #12

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1117. Min Act: -0.1700

Data Index: 4521639 (Open Web Text)

Max Activating Token Index: 296

Text #13

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1308. Min Act: -0.1700

Data Index: 2450130 (Open Web Text)

Max Activating Token Index: 417

Text #14

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.0995. Min Act: -0.1700

Data Index: 7658159 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.0861. Min Act: -0.1700

Data Index: 173449 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.0698. Min Act: -0.1700

Data Index: 3536158 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.1003. Min Act: -0.1700

Data Index: 4694678 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.0696. Min Act: -0.1700

Data Index: 3439006 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 4.3493. Min Range: -4.3493

Max Act: 4.0261. Min Act: -0.1700

Data Index: 3886392 (Open Web Text)

Max Activating Token Index: 498