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

Dataset: Open Web Text

Neuron 604 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: 3.9228. Min Range: -3.9228

Max Act: 3.9228. Min Act: -0.1700

Data Index: 231406 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8433. Min Act: -0.1700

Data Index: 4761174 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8428. Min Act: -0.1700

Data Index: 3984188 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8335. Min Act: -0.1700

Data Index: 2233704 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8229. Min Act: -0.1700

Data Index: 2305302 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8120. Min Act: -0.1700

Data Index: 7285978 (Open Web Text)

Max Activating Token Index: 649

Text #6

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8016. Min Act: -0.1700

Data Index: 2826625 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8050. Min Act: -0.1700

Data Index: 7935823 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8204. Min Act: -0.1700

Data Index: 3569124 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8036. Min Act: -0.1700

Data Index: 4050582 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8260. Min Act: -0.1700

Data Index: 3218429 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.8076. Min Act: -0.1700

Data Index: 2115537 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.7992. Min Act: -0.1700

Data Index: 3240221 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.7765. Min Act: -0.1700

Data Index: 3230424 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.7720. Min Act: -0.1700

Data Index: 2194911 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.7749. Min Act: -0.1700

Data Index: 5148032 (Open Web Text)

Max Activating Token Index: 969

Text #16

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.7910. Min Act: -0.1700

Data Index: 3164649 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.7881. Min Act: -0.1700

Data Index: 4217541 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.7910. Min Act: -0.1700

Data Index: 783997 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9228. Min Range: -3.9228

Max Act: 3.7810. Min Act: -0.1700

Data Index: 2929004 (Open Web Text)

Max Activating Token Index: 9