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

Dataset: Open Web Text

Neuron 3056 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: 4.3334. Min Range: -4.3334

Max Act: 4.3334. Min Act: -0.1700

Data Index: 6024975 (Open Web Text)

Max Activating Token Index: 866

Text #1

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.2682. Min Act: -0.1700

Data Index: 8253696 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.2362. Min Act: -0.1700

Data Index: 245875 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0912. Min Act: -0.1700

Data Index: 3918076 (Open Web Text)

Max Activating Token Index: 755

Text #4

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0974. Min Act: -0.1700

Data Index: 6302741 (Open Web Text)

Max Activating Token Index: 735

Text #5

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0918. Min Act: -0.1700

Data Index: 8347467 (Open Web Text)

Max Activating Token Index: 953

Text #6

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0805. Min Act: -0.1700

Data Index: 2967340 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0493. Min Act: -0.1700

Data Index: 1989058 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0513. Min Act: -0.1700

Data Index: 6866675 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0308. Min Act: -0.1700

Data Index: 6382707 (Open Web Text)

Max Activating Token Index: 757

Text #10

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0260. Min Act: -0.1700

Data Index: 6411355 (Open Web Text)

Max Activating Token Index: 898

Text #11

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9755. Min Act: -0.1700

Data Index: 2540216 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9913. Min Act: -0.1700

Data Index: 2994955 (Open Web Text)

Max Activating Token Index: 935

Text #13

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9568. Min Act: -0.1700

Data Index: 7648575 (Open Web Text)

Max Activating Token Index: 263

Text #14

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9600. Min Act: -0.1700

Data Index: 968331 (Open Web Text)

Max Activating Token Index: 321

Text #15

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9686. Min Act: -0.1700

Data Index: 4363123 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9645. Min Act: -0.1700

Data Index: 6250148 (Open Web Text)

Max Activating Token Index: 531

Text #17

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9027. Min Act: -0.1700

Data Index: 7302904 (Open Web Text)

Max Activating Token Index: 805

Text #18

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9116. Min Act: -0.1700

Data Index: 3003599 (Open Web Text)

Max Activating Token Index: 637

Text #19

Max Range: 4.3334. Min Range: -4.3334

Max Act: 3.9249. Min Act: -0.1700

Data Index: 4870303 (Open Web Text)

Max Activating Token Index: 361