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

Dataset: Open Web Text

Neuron 2349 in Layer 5

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: 2.3698. Min Range: -2.3698

Max Act: 2.3633. Min Act: -0.1700

Data Index: 804159 (Open Web Text)

Max Activating Token Index: 959

Text #1

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.3698. Min Act: -0.1700

Data Index: 6146450 (Open Web Text)

Max Activating Token Index: 974

Text #2

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2954. Min Act: -0.1700

Data Index: 2859078 (Open Web Text)

Max Activating Token Index: 368

Text #3

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2678. Min Act: -0.1700

Data Index: 1067877 (Open Web Text)

Max Activating Token Index: 1015

Text #4

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2897. Min Act: -0.1700

Data Index: 3930808 (Open Web Text)

Max Activating Token Index: 211

Text #5

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2841. Min Act: -0.1700

Data Index: 2369344 (Open Web Text)

Max Activating Token Index: 379

Text #6

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2683. Min Act: -0.1700

Data Index: 1380949 (Open Web Text)

Max Activating Token Index: 867

Text #7

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2761. Min Act: -0.1700

Data Index: 656500 (Open Web Text)

Max Activating Token Index: 225

Text #8

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2657. Min Act: -0.1700

Data Index: 2745020 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2553. Min Act: -0.1700

Data Index: 1301078 (Open Web Text)

Max Activating Token Index: 892

Text #10

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2450. Min Act: -0.1700

Data Index: 564019 (Open Web Text)

Max Activating Token Index: 839

Text #11

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2459. Min Act: -0.1700

Data Index: 5996052 (Open Web Text)

Max Activating Token Index: 662

Text #12

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2394. Min Act: -0.1700

Data Index: 3889627 (Open Web Text)

Max Activating Token Index: 526

Text #13

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2557. Min Act: -0.1700

Data Index: 5302035 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2612. Min Act: -0.1700

Data Index: 190204 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2446. Min Act: -0.1700

Data Index: 1117425 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2279. Min Act: -0.1700

Data Index: 2280479 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2346. Min Act: -0.1700

Data Index: 390984 (Open Web Text)

Max Activating Token Index: 607

Text #18

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2287. Min Act: -0.1700

Data Index: 3821815 (Open Web Text)

Max Activating Token Index: 264

Text #19

Max Range: 2.3698. Min Range: -2.3698

Max Act: 2.2319. Min Act: -0.1700

Data Index: 6013231 (Open Web Text)

Max Activating Token Index: 524