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

Dataset: Open Web Text

Neuron 1037 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: 4.0340. Min Range: -4.0340

Max Act: 4.0340. Min Act: -0.1700

Data Index: 3536382 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.9604. Min Act: -0.1700

Data Index: 5988884 (Open Web Text)

Max Activating Token Index: 131

Text #2

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7990. Min Act: -0.1700

Data Index: 1540236 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7642. Min Act: -0.1700

Data Index: 5446747 (Open Web Text)

Max Activating Token Index: 129

Text #4

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7333. Min Act: -0.1700

Data Index: 4754904 (Open Web Text)

Max Activating Token Index: 284

Text #5

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7385. Min Act: -0.1700

Data Index: 3653681 (Open Web Text)

Max Activating Token Index: 408

Text #6

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7368. Min Act: -0.1700

Data Index: 5178672 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6839. Min Act: -0.1700

Data Index: 4308072 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7102. Min Act: -0.1700

Data Index: 958722 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7172. Min Act: -0.1700

Data Index: 1089550 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6995. Min Act: -0.1700

Data Index: 2188502 (Open Web Text)

Max Activating Token Index: 276

Text #11

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7228. Min Act: -0.1700

Data Index: 1535036 (Open Web Text)

Max Activating Token Index: 123

Text #12

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7306. Min Act: -0.1700

Data Index: 2920537 (Open Web Text)

Max Activating Token Index: 185

Text #13

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6867. Min Act: -0.1700

Data Index: 252791 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6803. Min Act: -0.1700

Data Index: 6453796 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6641. Min Act: -0.1700

Data Index: 1377783 (Open Web Text)

Max Activating Token Index: 964

Text #16

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6771. Min Act: -0.1700

Data Index: 2475012 (Open Web Text)

Max Activating Token Index: 447

Text #17

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6836. Min Act: -0.1700

Data Index: 7086260 (Open Web Text)

Max Activating Token Index: 221

Text #18

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.7001. Min Act: -0.1700

Data Index: 5124872 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 4.0340. Min Range: -4.0340

Max Act: 3.6633. Min Act: -0.1700

Data Index: 2807585 (Open Web Text)

Max Activating Token Index: 480