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

Dataset: Open Web Text

Neuron 2603 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: 2.9943. Min Range: -2.9943

Max Act: 2.9943. Min Act: -0.1700

Data Index: 3717371 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9754. Min Act: -0.1700

Data Index: 3001160 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9555. Min Act: -0.1700

Data Index: 6597109 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9412. Min Act: -0.1700

Data Index: 3367223 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9252. Min Act: -0.1700

Data Index: 1667454 (Open Web Text)

Max Activating Token Index: 288

Text #5

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9090. Min Act: -0.1700

Data Index: 3737201 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9149. Min Act: -0.1700

Data Index: 8402837 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9167. Min Act: -0.1700

Data Index: 5439585 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9058. Min Act: -0.1700

Data Index: 5591511 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9054. Min Act: -0.1700

Data Index: 8286075 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9180. Min Act: -0.1700

Data Index: 4364942 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9042. Min Act: -0.1700

Data Index: 39623 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.9018. Min Act: -0.1700

Data Index: 5870419 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.8964. Min Act: -0.1700

Data Index: 2235100 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.8942. Min Act: -0.1700

Data Index: 6813831 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.8918. Min Act: -0.1700

Data Index: 2945279 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.8893. Min Act: -0.1700

Data Index: 3322389 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.8806. Min Act: -0.1700

Data Index: 260363 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.8720. Min Act: -0.1700

Data Index: 291136 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.8741. Min Act: -0.1700

Data Index: 4613902 (Open Web Text)

Max Activating Token Index: 12