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

Dataset: Open Web Text

Neuron 422 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: 4.5466. Min Range: -4.5466

Max Act: 4.5466. Min Act: -0.1700

Data Index: 8069252 (Open Web Text)

Max Activating Token Index: 111

Text #1

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.5194. Min Act: -0.1699

Data Index: 8656553 (Open Web Text)

Max Activating Token Index: 300

Text #2

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4591. Min Act: -0.1700

Data Index: 7579359 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4175. Min Act: -0.1700

Data Index: 6391490 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.3834. Min Act: -0.1700

Data Index: 5477185 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.3650. Min Act: -0.1700

Data Index: 6311372 (Open Web Text)

Max Activating Token Index: 175

Text #6

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4484. Min Act: -0.1700

Data Index: 6024167 (Open Web Text)

Max Activating Token Index: 485

Text #7

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4542. Min Act: -0.1700

Data Index: 1365174 (Open Web Text)

Max Activating Token Index: 208

Text #8

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4436. Min Act: -0.1700

Data Index: 3553123 (Open Web Text)

Max Activating Token Index: 446

Text #9

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4146. Min Act: -0.1700

Data Index: 5554905 (Open Web Text)

Max Activating Token Index: 417

Text #10

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.5285. Min Act: -0.1700

Data Index: 4300015 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.3717. Min Act: -0.1699

Data Index: 2731474 (Open Web Text)

Max Activating Token Index: 502

Text #12

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.3888. Min Act: -0.1697

Data Index: 5784576 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4223. Min Act: -0.1700

Data Index: 7274820 (Open Web Text)

Max Activating Token Index: 207

Text #14

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4722. Min Act: -0.1697

Data Index: 3270607 (Open Web Text)

Max Activating Token Index: 75

Text #15

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.3473. Min Act: -0.1699

Data Index: 5385688 (Open Web Text)

Max Activating Token Index: 633

Text #16

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4060. Min Act: -0.1700

Data Index: 3303374 (Open Web Text)

Max Activating Token Index: 382

Text #17

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.3732. Min Act: -0.1700

Data Index: 8249487 (Open Web Text)

Max Activating Token Index: 440

Text #18

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4342. Min Act: -0.1700

Data Index: 8353886 (Open Web Text)

Max Activating Token Index: 487

Text #19

Max Range: 4.5466. Min Range: -4.5466

Max Act: 4.4652. Min Act: -0.1693

Data Index: 3327263 (Open Web Text)

Max Activating Token Index: 360