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

Dataset: Open Web Text

Neuron 1424 in Layer 3

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: 4.5154. Min Range: -4.5154

Max Act: 4.5154. Min Act: -0.1700

Data Index: 7114751 (Open Web Text)

Max Activating Token Index: 56

Text #1

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.3471. Min Act: -0.1700

Data Index: 1313910 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2627. Min Act: -0.1700

Data Index: 1177568 (Open Web Text)

Max Activating Token Index: 968

Text #3

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.2342. Min Act: -0.1700

Data Index: 5009586 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.1682. Min Act: -0.1700

Data Index: 2937357 (Open Web Text)

Max Activating Token Index: 582

Text #5

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.0507. Min Act: -0.1700

Data Index: 7410513 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.0454. Min Act: -0.1700

Data Index: 1664964 (Open Web Text)

Max Activating Token Index: 724

Text #7

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.0394. Min Act: -0.1700

Data Index: 7869914 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9954. Min Act: -0.1700

Data Index: 2743960 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 4.5154. Min Range: -4.5154

Max Act: 4.0219. Min Act: -0.1700

Data Index: 7614069 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9876. Min Act: -0.1700

Data Index: 2492614 (Open Web Text)

Max Activating Token Index: 244

Text #11

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9957. Min Act: -0.1700

Data Index: 4571116 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9846. Min Act: -0.1700

Data Index: 6607996 (Open Web Text)

Max Activating Token Index: 776

Text #13

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9888. Min Act: -0.1700

Data Index: 6922388 (Open Web Text)

Max Activating Token Index: 315

Text #14

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9535. Min Act: -0.1700

Data Index: 7538823 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9961. Min Act: -0.1700

Data Index: 2103202 (Open Web Text)

Max Activating Token Index: 937

Text #16

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9810. Min Act: -0.1700

Data Index: 8600633 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9554. Min Act: -0.1700

Data Index: 3772238 (Open Web Text)

Max Activating Token Index: 833

Text #18

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9258. Min Act: -0.1700

Data Index: 2215112 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 4.5154. Min Range: -4.5154

Max Act: 3.9157. Min Act: -0.1700

Data Index: 1181366 (Open Web Text)

Max Activating Token Index: 856