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

Dataset: Open Web Text

Neuron 412 in Layer 6

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: 3.4159. Min Range: -3.4159

Max Act: 3.4159. Min Act: -0.1700

Data Index: 89441 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.3964. Min Act: -0.1700

Data Index: 2306108 (Open Web Text)

Max Activating Token Index: 809

Text #2

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.3627. Min Act: -0.1700

Data Index: 359453 (Open Web Text)

Max Activating Token Index: 967

Text #3

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.3582. Min Act: -0.1700

Data Index: 6756411 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.3107. Min Act: -0.1700

Data Index: 208018 (Open Web Text)

Max Activating Token Index: 961

Text #5

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.3203. Min Act: -0.1700

Data Index: 3344245 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.3239. Min Act: -0.1700

Data Index: 7374323 (Open Web Text)

Max Activating Token Index: 975

Text #7

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.3180. Min Act: -0.1700

Data Index: 5245994 (Open Web Text)

Max Activating Token Index: 74

Text #8

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2750. Min Act: -0.1700

Data Index: 2065807 (Open Web Text)

Max Activating Token Index: 267

Text #9

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2864. Min Act: -0.1700

Data Index: 5015164 (Open Web Text)

Max Activating Token Index: 965

Text #10

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2814. Min Act: -0.1700

Data Index: 8549351 (Open Web Text)

Max Activating Token Index: 977

Text #11

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2709. Min Act: -0.1700

Data Index: 2954929 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2814. Min Act: -0.1700

Data Index: 6570225 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2573. Min Act: -0.1700

Data Index: 8385178 (Open Web Text)

Max Activating Token Index: 725

Text #14

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2588. Min Act: -0.1700

Data Index: 1847765 (Open Web Text)

Max Activating Token Index: 318

Text #15

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2229. Min Act: -0.1700

Data Index: 6161621 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2263. Min Act: -0.1700

Data Index: 2565451 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2619. Min Act: -0.1700

Data Index: 4828922 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2523. Min Act: -0.1700

Data Index: 5873612 (Open Web Text)

Max Activating Token Index: 834

Text #19

Max Range: 3.4159. Min Range: -3.4159

Max Act: 3.2568. Min Act: -0.1700

Data Index: 3418339 (Open Web Text)

Max Activating Token Index: 582