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

Dataset: Open Web Text

Neuron 1986 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: 3.7032. Min Range: -3.7032

Max Act: 3.7032. Min Act: -0.1700

Data Index: 7624146 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.5476. Min Act: -0.1700

Data Index: 8362856 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4485. Min Act: -0.1700

Data Index: 6082112 (Open Web Text)

Max Activating Token Index: 221

Text #3

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.3956. Min Act: -0.1700

Data Index: 54997 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4092. Min Act: -0.1700

Data Index: 295152 (Open Web Text)

Max Activating Token Index: 591

Text #5

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.3889. Min Act: -0.1700

Data Index: 3003836 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.3591. Min Act: -0.1700

Data Index: 7006064 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.3278. Min Act: -0.1700

Data Index: 8595743 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.3321. Min Act: -0.1700

Data Index: 8508854 (Open Web Text)

Max Activating Token Index: 886

Text #9

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.3075. Min Act: -0.1700

Data Index: 2476292 (Open Web Text)

Max Activating Token Index: 253

Text #10

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2778. Min Act: -0.1700

Data Index: 8282983 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.3152. Min Act: -0.1700

Data Index: 3698760 (Open Web Text)

Max Activating Token Index: 246

Text #12

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2831. Min Act: -0.1700

Data Index: 8593329 (Open Web Text)

Max Activating Token Index: 184

Text #13

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2890. Min Act: -0.1700

Data Index: 2608892 (Open Web Text)

Max Activating Token Index: 933

Text #14

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2784. Min Act: -0.1700

Data Index: 3253328 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2809. Min Act: -0.1700

Data Index: 2012559 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2871. Min Act: -0.1700

Data Index: 5154181 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.3027. Min Act: -0.1700

Data Index: 8315355 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2706. Min Act: -0.1700

Data Index: 1648467 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.2599. Min Act: -0.1700

Data Index: 2917855 (Open Web Text)

Max Activating Token Index: 448