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

Dataset: Open Web Text

Neuron 2743 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: 4.6586. Min Range: -4.6586

Max Act: 4.6586. Min Act: -0.1700

Data Index: 1261097 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.6088. Min Act: -0.1700

Data Index: 7935558 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5703. Min Act: -0.1700

Data Index: 2212900 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5598. Min Act: -0.1700

Data Index: 207084 (Open Web Text)

Max Activating Token Index: 734

Text #4

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5802. Min Act: -0.1700

Data Index: 6892609 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5441. Min Act: -0.1700

Data Index: 5728878 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5403. Min Act: -0.1700

Data Index: 5891662 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5328. Min Act: -0.1700

Data Index: 5939647 (Open Web Text)

Max Activating Token Index: 48

Text #8

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5347. Min Act: -0.1700

Data Index: 4219745 (Open Web Text)

Max Activating Token Index: 806

Text #9

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5295. Min Act: -0.1700

Data Index: 7079402 (Open Web Text)

Max Activating Token Index: 45

Text #10

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.4888. Min Act: -0.1700

Data Index: 4479939 (Open Web Text)

Max Activating Token Index: 417

Text #11

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.4946. Min Act: -0.1700

Data Index: 2077106 (Open Web Text)

Max Activating Token Index: 266

Text #12

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5007. Min Act: -0.1700

Data Index: 1119297 (Open Web Text)

Max Activating Token Index: 607

Text #13

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5142. Min Act: -0.1700

Data Index: 1100626 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5006. Min Act: -0.1700

Data Index: 7874658 (Open Web Text)

Max Activating Token Index: 140

Text #15

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5063. Min Act: -0.1700

Data Index: 4121366 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5086. Min Act: -0.1700

Data Index: 6861398 (Open Web Text)

Max Activating Token Index: 375

Text #17

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.4922. Min Act: -0.1700

Data Index: 5956560 (Open Web Text)

Max Activating Token Index: 971

Text #18

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.5113. Min Act: -0.1700

Data Index: 3111414 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 4.6586. Min Range: -4.6586

Max Act: 4.4937. Min Act: -0.1700

Data Index: 5821185 (Open Web Text)

Max Activating Token Index: 571