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

Dataset: Open Web Text

Neuron 123 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: 4.9736. Min Range: -4.9736

Max Act: 4.9736. Min Act: -0.1700

Data Index: 8350312 (Open Web Text)

Max Activating Token Index: 580

Text #1

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.9253. Min Act: -0.1700

Data Index: 8320704 (Open Web Text)

Max Activating Token Index: 163

Text #2

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.9232. Min Act: -0.1700

Data Index: 8350309 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.8676. Min Act: -0.1700

Data Index: 8350311 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.8554. Min Act: -0.1700

Data Index: 2711077 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.8323. Min Act: -0.1700

Data Index: 8350310 (Open Web Text)

Max Activating Token Index: 485

Text #6

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7986. Min Act: -0.1700

Data Index: 4674003 (Open Web Text)

Max Activating Token Index: 42

Text #7

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7740. Min Act: -0.1700

Data Index: 6239913 (Open Web Text)

Max Activating Token Index: 423

Text #8

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7844. Min Act: -0.1700

Data Index: 8452587 (Open Web Text)

Max Activating Token Index: 440

Text #9

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7826. Min Act: -0.1700

Data Index: 5500023 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7730. Min Act: -0.1700

Data Index: 4333731 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7557. Min Act: -0.1700

Data Index: 6983149 (Open Web Text)

Max Activating Token Index: 223

Text #12

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7679. Min Act: -0.1700

Data Index: 6000090 (Open Web Text)

Max Activating Token Index: 624

Text #13

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7407. Min Act: -0.1700

Data Index: 221665 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7433. Min Act: -0.1700

Data Index: 1321092 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7651. Min Act: -0.1700

Data Index: 4709286 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7547. Min Act: -0.1700

Data Index: 401435 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7639. Min Act: -0.1700

Data Index: 1919955 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7179. Min Act: -0.1700

Data Index: 6019946 (Open Web Text)

Max Activating Token Index: 125

Text #19

Max Range: 4.9736. Min Range: -4.9736

Max Act: 4.7290. Min Act: -0.1700

Data Index: 3013876 (Open Web Text)

Max Activating Token Index: 156