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

Dataset: Open Web Text

Neuron 233 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: 3.5069. Min Range: -3.5069

Max Act: 3.5069. Min Act: -0.1700

Data Index: 4125619 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.4281. Min Act: -0.1700

Data Index: 6818739 (Open Web Text)

Max Activating Token Index: 346

Text #2

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.3475. Min Act: -0.1700

Data Index: 8595666 (Open Web Text)

Max Activating Token Index: 746

Text #3

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.3469. Min Act: -0.1700

Data Index: 903329 (Open Web Text)

Max Activating Token Index: 895

Text #4

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.3245. Min Act: -0.1700

Data Index: 8494773 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.3032. Min Act: -0.1700

Data Index: 5944263 (Open Web Text)

Max Activating Token Index: 788

Text #6

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2677. Min Act: -0.1700

Data Index: 5680974 (Open Web Text)

Max Activating Token Index: 156

Text #7

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2802. Min Act: -0.1700

Data Index: 1479933 (Open Web Text)

Max Activating Token Index: 798

Text #8

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2591. Min Act: -0.1700

Data Index: 910605 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2620. Min Act: -0.1700

Data Index: 2850814 (Open Web Text)

Max Activating Token Index: 612

Text #10

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2443. Min Act: -0.1700

Data Index: 2850813 (Open Web Text)

Max Activating Token Index: 784

Text #11

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2434. Min Act: -0.1700

Data Index: 6084573 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2426. Min Act: -0.1700

Data Index: 7834567 (Open Web Text)

Max Activating Token Index: 156

Text #13

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2315. Min Act: -0.1700

Data Index: 3374837 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2287. Min Act: -0.1700

Data Index: 1394980 (Open Web Text)

Max Activating Token Index: 494

Text #15

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.1987. Min Act: -0.1700

Data Index: 3800488 (Open Web Text)

Max Activating Token Index: 571

Text #16

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2035. Min Act: -0.1700

Data Index: 5151499 (Open Web Text)

Max Activating Token Index: 889

Text #17

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2263. Min Act: -0.1700

Data Index: 6096846 (Open Web Text)

Max Activating Token Index: 945

Text #18

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2134. Min Act: -0.1700

Data Index: 1873088 (Open Web Text)

Max Activating Token Index: 646

Text #19

Max Range: 3.5069. Min Range: -3.5069

Max Act: 3.2205. Min Act: -0.1700

Data Index: 1496952 (Open Web Text)

Max Activating Token Index: 835