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

Dataset: Open Web Text

Neuron 396 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: 1.7186. Min Range: -1.7186

Max Act: 1.7186. Min Act: -0.1700

Data Index: 4772970 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.7017. Min Act: -0.1700

Data Index: 7327665 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.7030. Min Act: -0.1700

Data Index: 6419021 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6684. Min Act: -0.1700

Data Index: 3999634 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6579. Min Act: -0.1700

Data Index: 5190653 (Open Web Text)

Max Activating Token Index: 199

Text #5

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6592. Min Act: -0.1700

Data Index: 6564676 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6477. Min Act: -0.1700

Data Index: 6072803 (Open Web Text)

Max Activating Token Index: 617

Text #7

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6520. Min Act: -0.1700

Data Index: 6607372 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6489. Min Act: -0.1700

Data Index: 7087475 (Open Web Text)

Max Activating Token Index: 47

Text #9

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6497. Min Act: -0.1700

Data Index: 3896262 (Open Web Text)

Max Activating Token Index: 769

Text #10

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6509. Min Act: -0.1700

Data Index: 5293799 (Open Web Text)

Max Activating Token Index: 356

Text #11

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6414. Min Act: -0.1700

Data Index: 126017 (Open Web Text)

Max Activating Token Index: 798

Text #12

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6442. Min Act: -0.1700

Data Index: 493773 (Open Web Text)

Max Activating Token Index: 115

Text #13

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6472. Min Act: -0.1700

Data Index: 5972311 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6411. Min Act: -0.1700

Data Index: 5723815 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6385. Min Act: -0.1700

Data Index: 6885603 (Open Web Text)

Max Activating Token Index: 997

Text #16

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6401. Min Act: -0.1700

Data Index: 7353183 (Open Web Text)

Max Activating Token Index: 278

Text #17

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6443. Min Act: -0.1700

Data Index: 7557866 (Open Web Text)

Max Activating Token Index: 154

Text #18

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6409. Min Act: -0.1700

Data Index: 212259 (Open Web Text)

Max Activating Token Index: 193

Text #19

Max Range: 1.7186. Min Range: -1.7186

Max Act: 1.6363. Min Act: -0.1699

Data Index: 3794498 (Open Web Text)

Max Activating Token Index: 791