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

Dataset: Open Web Text

Neuron 555 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: 3.1293. Min Range: -3.1293

Max Act: 3.1293. Min Act: -0.1700

Data Index: 142257 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0877. Min Act: -0.1700

Data Index: 2475434 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0712. Min Act: -0.1700

Data Index: 6242671 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0537. Min Act: -0.1700

Data Index: 4831839 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0396. Min Act: -0.1700

Data Index: 6847128 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0206. Min Act: -0.1700

Data Index: 5530283 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0295. Min Act: -0.1700

Data Index: 1519745 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0179. Min Act: -0.1700

Data Index: 7216239 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0318. Min Act: -0.1700

Data Index: 3449840 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0302. Min Act: -0.1700

Data Index: 950672 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0259. Min Act: -0.1700

Data Index: 5594980 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0194. Min Act: -0.1700

Data Index: 6364581 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0139. Min Act: -0.1700

Data Index: 747845 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0090. Min Act: -0.1700

Data Index: 8015432 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0093. Min Act: -0.1700

Data Index: 4747314 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0144. Min Act: -0.1700

Data Index: 2810856 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0156. Min Act: -0.1700

Data Index: 2167215 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0117. Min Act: -0.1700

Data Index: 3040581 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0001. Min Act: -0.1700

Data Index: 382195 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.1293. Min Range: -3.1293

Max Act: 3.0034. Min Act: -0.1700

Data Index: 4935151 (Open Web Text)

Max Activating Token Index: 2