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

Dataset: Open Web Text

Neuron 1153 in Layer 4

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: 4.7958. Min Range: -4.7958

Max Act: 4.7958. Min Act: -0.1700

Data Index: 4439874 (Open Web Text)

Max Activating Token Index: 832

Text #1

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.6928. Min Act: -0.1700

Data Index: 2198469 (Open Web Text)

Max Activating Token Index: 388

Text #2

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.5574. Min Act: -0.1700

Data Index: 7602370 (Open Web Text)

Max Activating Token Index: 389

Text #3

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.5903. Min Act: -0.1700

Data Index: 6176105 (Open Web Text)

Max Activating Token Index: 598

Text #4

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.5439. Min Act: -0.1700

Data Index: 2606878 (Open Web Text)

Max Activating Token Index: 135

Text #5

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4958. Min Act: -0.1700

Data Index: 6690316 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.3706. Min Act: -0.1700

Data Index: 7560074 (Open Web Text)

Max Activating Token Index: 421

Text #7

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4154. Min Act: -0.1700

Data Index: 7439986 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4910. Min Act: -0.1700

Data Index: 7417552 (Open Web Text)

Max Activating Token Index: 282

Text #9

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4987. Min Act: -0.1700

Data Index: 7251619 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4964. Min Act: -0.1700

Data Index: 2452197 (Open Web Text)

Max Activating Token Index: 744

Text #11

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4749. Min Act: -0.1700

Data Index: 4588471 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4393. Min Act: -0.1700

Data Index: 2413159 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4327. Min Act: -0.1700

Data Index: 4741176 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4691. Min Act: -0.1700

Data Index: 957479 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4475. Min Act: -0.1700

Data Index: 640489 (Open Web Text)

Max Activating Token Index: 266

Text #16

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4351. Min Act: -0.1700

Data Index: 4198710 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.4958. Min Act: -0.1700

Data Index: 4440605 (Open Web Text)

Max Activating Token Index: 868

Text #18

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.3163. Min Act: -0.1700

Data Index: 1068985 (Open Web Text)

Max Activating Token Index: 184

Text #19

Max Range: 4.7958. Min Range: -4.7958

Max Act: 4.3955. Min Act: -0.1700

Data Index: 5694792 (Open Web Text)

Max Activating Token Index: 618