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

Dataset: Open Web Text

Neuron 2452 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: 2.5489. Min Range: -2.5489

Max Act: 2.5489. Min Act: -0.1700

Data Index: 8786956 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.5111. Min Act: -0.1700

Data Index: 8217634 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.5124. Min Act: -0.1700

Data Index: 8164358 (Open Web Text)

Max Activating Token Index: 508

Text #3

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4643. Min Act: -0.1700

Data Index: 6079412 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4666. Min Act: -0.1700

Data Index: 912780 (Open Web Text)

Max Activating Token Index: 1009

Text #5

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4647. Min Act: -0.1700

Data Index: 7519267 (Open Web Text)

Max Activating Token Index: 680

Text #6

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4530. Min Act: -0.1700

Data Index: 8142194 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4545. Min Act: -0.1700

Data Index: 6340600 (Open Web Text)

Max Activating Token Index: 650

Text #8

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4606. Min Act: -0.1700

Data Index: 6599794 (Open Web Text)

Max Activating Token Index: 337

Text #9

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4683. Min Act: -0.1700

Data Index: 1122748 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4539. Min Act: -0.1700

Data Index: 116122 (Open Web Text)

Max Activating Token Index: 1010

Text #11

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4582. Min Act: -0.1700

Data Index: 7436092 (Open Web Text)

Max Activating Token Index: 609

Text #12

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4432. Min Act: -0.1700

Data Index: 4783887 (Open Web Text)

Max Activating Token Index: 363

Text #13

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4605. Min Act: -0.1700

Data Index: 6509511 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4327. Min Act: -0.1700

Data Index: 4354935 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4495. Min Act: -0.1700

Data Index: 6280088 (Open Web Text)

Max Activating Token Index: 682

Text #16

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4250. Min Act: -0.1700

Data Index: 4894388 (Open Web Text)

Max Activating Token Index: 365

Text #17

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4282. Min Act: -0.1700

Data Index: 3131994 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4279. Min Act: -0.1700

Data Index: 2150519 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 2.5489. Min Range: -2.5489

Max Act: 2.4220. Min Act: -0.1700

Data Index: 2287920 (Open Web Text)

Max Activating Token Index: 897