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

Dataset: Open Web Text

Neuron 2441 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: 3.3675. Min Range: -3.3675

Max Act: 3.3675. Min Act: -0.1700

Data Index: 1890592 (Open Web Text)

Max Activating Token Index: 122

Text #1

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2244. Min Act: -0.1700

Data Index: 4911760 (Open Web Text)

Max Activating Token Index: 261

Text #2

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2422. Min Act: -0.1700

Data Index: 6874420 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.2028. Min Act: -0.1700

Data Index: 3793445 (Open Web Text)

Max Activating Token Index: 394

Text #4

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1540. Min Act: -0.1700

Data Index: 3097164 (Open Web Text)

Max Activating Token Index: 409

Text #5

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1559. Min Act: -0.1700

Data Index: 6514835 (Open Web Text)

Max Activating Token Index: 914

Text #6

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1533. Min Act: -0.1700

Data Index: 1037573 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1471. Min Act: -0.1700

Data Index: 3946425 (Open Web Text)

Max Activating Token Index: 589

Text #8

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1519. Min Act: -0.1700

Data Index: 2739822 (Open Web Text)

Max Activating Token Index: 574

Text #9

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1251. Min Act: -0.1700

Data Index: 5287652 (Open Web Text)

Max Activating Token Index: 184

Text #10

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1220. Min Act: -0.1700

Data Index: 6276530 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1094. Min Act: -0.1700

Data Index: 3097162 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.1307. Min Act: -0.1700

Data Index: 7669665 (Open Web Text)

Max Activating Token Index: 383

Text #13

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.0930. Min Act: -0.1700

Data Index: 3119014 (Open Web Text)

Max Activating Token Index: 813

Text #14

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.0951. Min Act: -0.1700

Data Index: 2342148 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.0606. Min Act: -0.1700

Data Index: 2149732 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.0602. Min Act: -0.1700

Data Index: 3512741 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.0659. Min Act: -0.1700

Data Index: 1476988 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.0656. Min Act: -0.1700

Data Index: 7683349 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 3.3675. Min Range: -3.3675

Max Act: 3.0851. Min Act: -0.1700

Data Index: 1286314 (Open Web Text)

Max Activating Token Index: 84