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

Dataset: Open Web Text

Neuron 2061 in Layer 0

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: 2.7882. Min Range: -2.7882

Max Act: 2.7882. Min Act: -0.1700

Data Index: 816743 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7792. Min Act: -0.1700

Data Index: 7445639 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7498. Min Act: -0.1700

Data Index: 1640910 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7547. Min Act: -0.1700

Data Index: 5080244 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7549. Min Act: -0.1700

Data Index: 4254781 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7707. Min Act: -0.1700

Data Index: 8334426 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7510. Min Act: -0.1700

Data Index: 6832492 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7296. Min Act: -0.1700

Data Index: 2889663 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7240. Min Act: -0.1700

Data Index: 544556 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7253. Min Act: -0.1700

Data Index: 1360885 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7197. Min Act: -0.1700

Data Index: 2550054 (Open Web Text)

Max Activating Token Index: 950

Text #11

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7226. Min Act: -0.1700

Data Index: 2506755 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7241. Min Act: -0.1700

Data Index: 3308265 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7231. Min Act: -0.1700

Data Index: 2603904 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7226. Min Act: -0.1700

Data Index: 2366211 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7251. Min Act: -0.1700

Data Index: 5641959 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7288. Min Act: -0.1700

Data Index: 1693692 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7226. Min Act: -0.1700

Data Index: 5130496 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7268. Min Act: -0.1700

Data Index: 3975644 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 2.7882. Min Range: -2.7882

Max Act: 2.7041. Min Act: -0.1700

Data Index: 4925026 (Open Web Text)

Max Activating Token Index: 2