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

Dataset: Open Web Text

Neuron 3022 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: 2.7477. Min Range: -2.7477

Max Act: 2.7477. Min Act: -0.1700

Data Index: 4385041 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6600. Min Act: -0.1700

Data Index: 5138984 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6641. Min Act: -0.1700

Data Index: 1230102 (Open Web Text)

Max Activating Token Index: 729

Text #3

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6600. Min Act: -0.1700

Data Index: 3218936 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6519. Min Act: -0.1700

Data Index: 3081291 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6569. Min Act: -0.1700

Data Index: 4672432 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6559. Min Act: -0.1700

Data Index: 1484818 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6426. Min Act: -0.1700

Data Index: 540240 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6361. Min Act: -0.1700

Data Index: 5827406 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6353. Min Act: -0.1700

Data Index: 4071267 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6342. Min Act: -0.1700

Data Index: 5907511 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6415. Min Act: -0.1700

Data Index: 8382784 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6424. Min Act: -0.1700

Data Index: 1254499 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6160. Min Act: -0.1700

Data Index: 5511508 (Open Web Text)

Max Activating Token Index: 81

Text #14

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6189. Min Act: -0.1700

Data Index: 4790940 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6126. Min Act: -0.1700

Data Index: 5935432 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6069. Min Act: -0.1700

Data Index: 3979213 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6272. Min Act: -0.1700

Data Index: 2143819 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6143. Min Act: -0.1700

Data Index: 6420885 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.7477. Min Range: -2.7477

Max Act: 2.6141. Min Act: -0.1700

Data Index: 2159025 (Open Web Text)

Max Activating Token Index: 4