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

Dataset: Open Web Text

Neuron 2445 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: 5.8938. Min Range: -5.8938

Max Act: 5.8938. Min Act: -0.1700

Data Index: 3549595 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.8525. Min Act: -0.1700

Data Index: 2066996 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.8001. Min Act: -0.1700

Data Index: 3304282 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.7537. Min Act: -0.1700

Data Index: 1191101 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.7631. Min Act: -0.1700

Data Index: 7458578 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.7639. Min Act: -0.1700

Data Index: 3304293 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.7249. Min Act: -0.1700

Data Index: 7454028 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.7129. Min Act: -0.1700

Data Index: 3881701 (Open Web Text)

Max Activating Token Index: 74

Text #8

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.7313. Min Act: -0.1700

Data Index: 3304281 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6876. Min Act: -0.1700

Data Index: 1191079 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6807. Min Act: -0.1700

Data Index: 1377967 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6516. Min Act: -0.1700

Data Index: 6767217 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6743. Min Act: -0.1700

Data Index: 585176 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6621. Min Act: -0.1700

Data Index: 5649612 (Open Web Text)

Max Activating Token Index: 99

Text #14

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6530. Min Act: -0.1700

Data Index: 3082322 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6198. Min Act: -0.1700

Data Index: 1191088 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6181. Min Act: -0.1700

Data Index: 3304285 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.6454. Min Act: -0.1700

Data Index: 8239109 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.5934. Min Act: -0.1700

Data Index: 7537821 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.8938. Min Range: -5.8938

Max Act: 5.5925. Min Act: -0.1700

Data Index: 641015 (Open Web Text)

Max Activating Token Index: 23