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

Dataset: Open Web Text

Neuron 2590 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: 3.4627. Min Range: -3.4627

Max Act: 3.4627. Min Act: -0.1700

Data Index: 4862290 (Open Web Text)

Max Activating Token Index: 210

Text #1

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.4559. Min Act: -0.1700

Data Index: 7226727 (Open Web Text)

Max Activating Token Index: 286

Text #2

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.4123. Min Act: -0.1700

Data Index: 1823514 (Open Web Text)

Max Activating Token Index: 357

Text #3

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.4079. Min Act: -0.1700

Data Index: 1557887 (Open Web Text)

Max Activating Token Index: 253

Text #4

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3801. Min Act: -0.1700

Data Index: 5445284 (Open Web Text)

Max Activating Token Index: 81

Text #5

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3585. Min Act: -0.1700

Data Index: 6014227 (Open Web Text)

Max Activating Token Index: 326

Text #6

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3618. Min Act: -0.1700

Data Index: 8707663 (Open Web Text)

Max Activating Token Index: 171

Text #7

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3519. Min Act: -0.1700

Data Index: 2701034 (Open Web Text)

Max Activating Token Index: 202

Text #8

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3681. Min Act: -0.1700

Data Index: 3162179 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3312. Min Act: -0.1700

Data Index: 187577 (Open Web Text)

Max Activating Token Index: 507

Text #10

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3295. Min Act: -0.1700

Data Index: 8122113 (Open Web Text)

Max Activating Token Index: 333

Text #11

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3215. Min Act: -0.1700

Data Index: 2754269 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3329. Min Act: -0.1700

Data Index: 3771598 (Open Web Text)

Max Activating Token Index: 153

Text #13

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.2993. Min Act: -0.1700

Data Index: 7944201 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.3007. Min Act: -0.1700

Data Index: 1343587 (Open Web Text)

Max Activating Token Index: 319

Text #15

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.2494. Min Act: -0.1700

Data Index: 2287030 (Open Web Text)

Max Activating Token Index: 246

Text #16

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.2874. Min Act: -0.1700

Data Index: 6606431 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.2692. Min Act: -0.1700

Data Index: 5771088 (Open Web Text)

Max Activating Token Index: 728

Text #18

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.2830. Min Act: -0.1700

Data Index: 5035285 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 3.4627. Min Range: -3.4627

Max Act: 3.2973. Min Act: -0.1700

Data Index: 6189929 (Open Web Text)

Max Activating Token Index: 849