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

Dataset: Open Web Text

Neuron 1184 in Layer 0

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: 3.6700. Min Range: -3.6700

Max Act: 3.6700. Min Act: -0.1700

Data Index: 3584092 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6669. Min Act: -0.1700

Data Index: 3848762 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6341. Min Act: -0.1700

Data Index: 988049 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6350. Min Act: -0.1700

Data Index: 450311 (Open Web Text)

Max Activating Token Index: 897

Text #4

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6491. Min Act: -0.1700

Data Index: 6923392 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6434. Min Act: -0.1700

Data Index: 3740424 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6010. Min Act: -0.1700

Data Index: 3739794 (Open Web Text)

Max Activating Token Index: 951

Text #7

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6118. Min Act: -0.1700

Data Index: 5986594 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6206. Min Act: -0.1700

Data Index: 5805633 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6139. Min Act: -0.1700

Data Index: 5478996 (Open Web Text)

Max Activating Token Index: 970

Text #10

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.5949. Min Act: -0.1700

Data Index: 64950 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6206. Min Act: -0.1700

Data Index: 4567662 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6147. Min Act: -0.1700

Data Index: 4336360 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6012. Min Act: -0.1700

Data Index: 4014301 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6056. Min Act: -0.1700

Data Index: 2425664 (Open Web Text)

Max Activating Token Index: 917

Text #15

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6143. Min Act: -0.1700

Data Index: 2403728 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6206. Min Act: -0.1700

Data Index: 1900124 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6137. Min Act: -0.1700

Data Index: 2312275 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6283. Min Act: -0.1700

Data Index: 753281 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6157. Min Act: -0.1700

Data Index: 1505874 (Open Web Text)

Max Activating Token Index: 5