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

Dataset: Open Web Text

Neuron 1102 in Layer 2

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: 4.3581. Min Range: -4.3581

Max Act: 4.3529. Min Act: -0.1700

Data Index: 6350737 (Open Web Text)

Max Activating Token Index: 134

Text #1

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.3581. Min Act: -0.1700

Data Index: 4100882 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.2883. Min Act: -0.1700

Data Index: 8621924 (Open Web Text)

Max Activating Token Index: 805

Text #3

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.2271. Min Act: -0.1700

Data Index: 1713067 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.2332. Min Act: -0.1700

Data Index: 4490701 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.2000. Min Act: -0.1700

Data Index: 6887581 (Open Web Text)

Max Activating Token Index: 125

Text #6

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.2125. Min Act: -0.1700

Data Index: 6432261 (Open Web Text)

Max Activating Token Index: 153

Text #7

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.2068. Min Act: -0.1700

Data Index: 8552980 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.1846. Min Act: -0.1700

Data Index: 6516035 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.1355. Min Act: -0.1700

Data Index: 5831315 (Open Web Text)

Max Activating Token Index: 114

Text #10

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.1270. Min Act: -0.1700

Data Index: 8602016 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.1200. Min Act: -0.1700

Data Index: 2627425 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.1060. Min Act: -0.1700

Data Index: 3040352 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.0890. Min Act: -0.1700

Data Index: 6593765 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.0661. Min Act: -0.1700

Data Index: 4138675 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.0478. Min Act: -0.1700

Data Index: 6669207 (Open Web Text)

Max Activating Token Index: 240

Text #16

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.0816. Min Act: -0.1700

Data Index: 2582517 (Open Web Text)

Max Activating Token Index: 326

Text #17

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.1087. Min Act: -0.1700

Data Index: 8078235 (Open Web Text)

Max Activating Token Index: 395

Text #18

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.0643. Min Act: -0.1700

Data Index: 417428 (Open Web Text)

Max Activating Token Index: 116

Text #19

Max Range: 4.3581. Min Range: -4.3581

Max Act: 4.0178. Min Act: -0.1700

Data Index: 3722793 (Open Web Text)

Max Activating Token Index: 476