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

Dataset: Open Web Text

Neuron 2448 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: 4.8983. Min Range: -4.8983

Max Act: 4.8983. Min Act: -0.1700

Data Index: 823380 (Open Web Text)

Max Activating Token Index: 717

Text #1

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.5626. Min Act: -0.1700

Data Index: 5495606 (Open Web Text)

Max Activating Token Index: 858

Text #2

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.4956. Min Act: -0.1700

Data Index: 3872966 (Open Web Text)

Max Activating Token Index: 825

Text #3

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.4335. Min Act: -0.1700

Data Index: 6046816 (Open Web Text)

Max Activating Token Index: 856

Text #4

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3968. Min Act: -0.1700

Data Index: 535641 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.4036. Min Act: -0.1700

Data Index: 8399790 (Open Web Text)

Max Activating Token Index: 572

Text #6

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3340. Min Act: -0.1700

Data Index: 7706082 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3534. Min Act: -0.1700

Data Index: 3778829 (Open Web Text)

Max Activating Token Index: 335

Text #8

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3566. Min Act: -0.1700

Data Index: 3541955 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3063. Min Act: -0.1700

Data Index: 1147178 (Open Web Text)

Max Activating Token Index: 410

Text #10

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.2923. Min Act: -0.1700

Data Index: 8428904 (Open Web Text)

Max Activating Token Index: 235

Text #11

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3170. Min Act: -0.1700

Data Index: 316222 (Open Web Text)

Max Activating Token Index: 669

Text #12

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3062. Min Act: -0.1700

Data Index: 4590582 (Open Web Text)

Max Activating Token Index: 206

Text #13

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3017. Min Act: -0.1700

Data Index: 6305068 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.2815. Min Act: -0.1700

Data Index: 762001 (Open Web Text)

Max Activating Token Index: 608

Text #15

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3353. Min Act: -0.1700

Data Index: 2145714 (Open Web Text)

Max Activating Token Index: 455

Text #16

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3227. Min Act: -0.1700

Data Index: 1707498 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.2851. Min Act: -0.1700

Data Index: 5640968 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.3094. Min Act: -0.1700

Data Index: 730936 (Open Web Text)

Max Activating Token Index: 130

Text #19

Max Range: 4.8983. Min Range: -4.8983

Max Act: 4.2657. Min Act: -0.1700

Data Index: 1853630 (Open Web Text)

Max Activating Token Index: 653