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

Dataset: Open Web Text

Neuron 2449 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: 4.5501. Min Range: -4.5501

Max Act: 4.5501. Min Act: -0.1700

Data Index: 3253648 (Open Web Text)

Max Activating Token Index: 646

Text #1

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.5387. Min Act: -0.1700

Data Index: 7828824 (Open Web Text)

Max Activating Token Index: 1018

Text #2

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.4548. Min Act: -0.1700

Data Index: 3537830 (Open Web Text)

Max Activating Token Index: 212

Text #3

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.4342. Min Act: -0.1700

Data Index: 2526554 (Open Web Text)

Max Activating Token Index: 997

Text #4

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.4349. Min Act: -0.1700

Data Index: 306209 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.4230. Min Act: -0.1700

Data Index: 5743697 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.4233. Min Act: -0.1700

Data Index: 2111545 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.4138. Min Act: -0.1700

Data Index: 4210160 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3988. Min Act: -0.1700

Data Index: 362503 (Open Web Text)

Max Activating Token Index: 821

Text #9

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3662. Min Act: -0.1700

Data Index: 3465885 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3786. Min Act: -0.1700

Data Index: 4379029 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3824. Min Act: -0.1700

Data Index: 3793667 (Open Web Text)

Max Activating Token Index: 619

Text #12

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3693. Min Act: -0.1700

Data Index: 3328941 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3317. Min Act: -0.1700

Data Index: 3461022 (Open Web Text)

Max Activating Token Index: 716

Text #14

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3618. Min Act: -0.1700

Data Index: 2850100 (Open Web Text)

Max Activating Token Index: 895

Text #15

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3213. Min Act: -0.1700

Data Index: 764353 (Open Web Text)

Max Activating Token Index: 473

Text #16

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.2980. Min Act: -0.1700

Data Index: 6964959 (Open Web Text)

Max Activating Token Index: 202

Text #17

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3020. Min Act: -0.1700

Data Index: 7213468 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.2903. Min Act: -0.1700

Data Index: 8011282 (Open Web Text)

Max Activating Token Index: 763

Text #19

Max Range: 4.5501. Min Range: -4.5501

Max Act: 4.3106. Min Act: -0.1700

Data Index: 4327174 (Open Web Text)

Max Activating Token Index: 910