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

Dataset: Open Web Text

Neuron 2738 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: 3.8152. Min Range: -3.8152

Max Act: 3.8152. Min Act: -0.1700

Data Index: 953304 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.7581. Min Act: -0.1700

Data Index: 7259291 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.7438. Min Act: -0.1700

Data Index: 4049218 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.7120. Min Act: -0.1700

Data Index: 2071782 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.7450. Min Act: -0.1700

Data Index: 1479494 (Open Web Text)

Max Activating Token Index: 331

Text #5

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.7447. Min Act: -0.1700

Data Index: 6283747 (Open Web Text)

Max Activating Token Index: 856

Text #6

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.7155. Min Act: -0.1700

Data Index: 7098669 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6610. Min Act: -0.1700

Data Index: 7994174 (Open Web Text)

Max Activating Token Index: 552

Text #8

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6626. Min Act: -0.1700

Data Index: 7116766 (Open Web Text)

Max Activating Token Index: 761

Text #9

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6687. Min Act: -0.1700

Data Index: 4687227 (Open Web Text)

Max Activating Token Index: 592

Text #10

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6784. Min Act: -0.1700

Data Index: 4259231 (Open Web Text)

Max Activating Token Index: 448

Text #11

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6952. Min Act: -0.1700

Data Index: 6809703 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6668. Min Act: -0.1700

Data Index: 4198083 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.7040. Min Act: -0.1700

Data Index: 8283981 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6511. Min Act: -0.1700

Data Index: 285089 (Open Web Text)

Max Activating Token Index: 221

Text #15

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6482. Min Act: -0.1700

Data Index: 2445924 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6407. Min Act: -0.1700

Data Index: 2589515 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6449. Min Act: -0.1700

Data Index: 27387 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6357. Min Act: -0.1700

Data Index: 4739434 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 3.8152. Min Range: -3.8152

Max Act: 3.6423. Min Act: -0.1700

Data Index: 5205346 (Open Web Text)

Max Activating Token Index: 11