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

Dataset: Open Web Text

Neuron 1180 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: 4.8460. Min Range: -4.8460

Max Act: 4.8460. Min Act: -0.1700

Data Index: 5505521 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.8123. Min Act: -0.1700

Data Index: 3174413 (Open Web Text)

Max Activating Token Index: 499

Text #2

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.8265. Min Act: -0.1700

Data Index: 3253328 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7972. Min Act: -0.1700

Data Index: 3861890 (Open Web Text)

Max Activating Token Index: 1011

Text #4

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7752. Min Act: -0.1700

Data Index: 2976351 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7605. Min Act: -0.1700

Data Index: 1048259 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7283. Min Act: -0.1700

Data Index: 1597789 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7488. Min Act: -0.1700

Data Index: 4863569 (Open Web Text)

Max Activating Token Index: 999

Text #8

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7519. Min Act: -0.1700

Data Index: 6983508 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7645. Min Act: -0.1700

Data Index: 579139 (Open Web Text)

Max Activating Token Index: 593

Text #10

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7553. Min Act: -0.1700

Data Index: 1997035 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7449. Min Act: -0.1700

Data Index: 1094297 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7127. Min Act: -0.1700

Data Index: 8368557 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7373. Min Act: -0.1700

Data Index: 4689058 (Open Web Text)

Max Activating Token Index: 1007

Text #14

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.7098. Min Act: -0.1700

Data Index: 2110465 (Open Web Text)

Max Activating Token Index: 169

Text #15

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6921. Min Act: -0.1700

Data Index: 6305243 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6800. Min Act: -0.1700

Data Index: 7710829 (Open Web Text)

Max Activating Token Index: 886

Text #17

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6857. Min Act: -0.1700

Data Index: 5154026 (Open Web Text)

Max Activating Token Index: 845

Text #18

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6750. Min Act: -0.1700

Data Index: 8226438 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 4.8460. Min Range: -4.8460

Max Act: 4.6778. Min Act: -0.1700

Data Index: 1206162 (Open Web Text)

Max Activating Token Index: 631