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

Dataset: Open Web Text

Neuron 338 in Layer 3

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: 3.1026. Min Range: -3.1026

Max Act: 3.1026. Min Act: -0.1700

Data Index: 2195925 (Open Web Text)

Max Activating Token Index: 209

Text #1

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.8213. Min Act: -0.1700

Data Index: 7644217 (Open Web Text)

Max Activating Token Index: 75

Text #2

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.8438. Min Act: -0.1700

Data Index: 4318225 (Open Web Text)

Max Activating Token Index: 849

Text #3

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7626. Min Act: -0.1700

Data Index: 1817878 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7960. Min Act: -0.1700

Data Index: 1817879 (Open Web Text)

Max Activating Token Index: 133

Text #5

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7748. Min Act: -0.1700

Data Index: 1817872 (Open Web Text)

Max Activating Token Index: 269

Text #6

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7708. Min Act: -0.1700

Data Index: 1817883 (Open Web Text)

Max Activating Token Index: 208

Text #7

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7650. Min Act: -0.1700

Data Index: 1817887 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7566. Min Act: -0.1700

Data Index: 8762444 (Open Web Text)

Max Activating Token Index: 957

Text #9

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7205. Min Act: -0.1700

Data Index: 8363833 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7788. Min Act: -0.1700

Data Index: 3906990 (Open Web Text)

Max Activating Token Index: 140

Text #11

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7486. Min Act: -0.1700

Data Index: 7631699 (Open Web Text)

Max Activating Token Index: 900

Text #12

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7880. Min Act: -0.1700

Data Index: 5918119 (Open Web Text)

Max Activating Token Index: 972

Text #13

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7362. Min Act: -0.1700

Data Index: 8026267 (Open Web Text)

Max Activating Token Index: 128

Text #14

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7591. Min Act: -0.1700

Data Index: 2755321 (Open Web Text)

Max Activating Token Index: 295

Text #15

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7624. Min Act: -0.1700

Data Index: 1817885 (Open Web Text)

Max Activating Token Index: 307

Text #16

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7405. Min Act: -0.1700

Data Index: 7426119 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7377. Min Act: -0.1700

Data Index: 6802179 (Open Web Text)

Max Activating Token Index: 138

Text #18

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7716. Min Act: -0.1700

Data Index: 709074 (Open Web Text)

Max Activating Token Index: 57

Text #19

Max Range: 3.1026. Min Range: -3.1026

Max Act: 2.7409. Min Act: -0.1700

Data Index: 1056459 (Open Web Text)

Max Activating Token Index: 156