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

Dataset: Open Web Text

Neuron 2920 in Layer 1

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: 3.6186. Min Range: -3.6186

Max Act: 3.6186. Min Act: -0.1700

Data Index: 4772602 (Open Web Text)

Max Activating Token Index: 64

Text #1

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.5473. Min Act: -0.1700

Data Index: 6195805 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4907. Min Act: -0.1700

Data Index: 7319455 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4546. Min Act: -0.1700

Data Index: 1762840 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4618. Min Act: -0.1700

Data Index: 6620048 (Open Web Text)

Max Activating Token Index: 883

Text #5

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4455. Min Act: -0.1700

Data Index: 594339 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4141. Min Act: -0.1700

Data Index: 7269956 (Open Web Text)

Max Activating Token Index: 788

Text #7

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4261. Min Act: -0.1700

Data Index: 8261015 (Open Web Text)

Max Activating Token Index: 43

Text #8

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4241. Min Act: -0.1700

Data Index: 4115358 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4345. Min Act: -0.1700

Data Index: 8325292 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4071. Min Act: -0.1700

Data Index: 288513 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.4132. Min Act: -0.1700

Data Index: 1659156 (Open Web Text)

Max Activating Token Index: 581

Text #12

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3901. Min Act: -0.1700

Data Index: 3813223 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3750. Min Act: -0.1700

Data Index: 141988 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3687. Min Act: -0.1700

Data Index: 4352605 (Open Web Text)

Max Activating Token Index: 347

Text #15

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3645. Min Act: -0.1700

Data Index: 3389783 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3557. Min Act: -0.1700

Data Index: 7558060 (Open Web Text)

Max Activating Token Index: 33

Text #17

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3348. Min Act: -0.1700

Data Index: 1614520 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3558. Min Act: -0.1700

Data Index: 8484477 (Open Web Text)

Max Activating Token Index: 721

Text #19

Max Range: 3.6186. Min Range: -3.6186

Max Act: 3.3574. Min Act: -0.1700

Data Index: 8672144 (Open Web Text)

Max Activating Token Index: 816