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

Dataset: Open Web Text

Neuron 2124 in Layer 3

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: 3.5440. Min Range: -3.5440

Max Act: 3.5440. Min Act: -0.1700

Data Index: 3769733 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.3962. Min Act: -0.1700

Data Index: 7757342 (Open Web Text)

Max Activating Token Index: 198

Text #2

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.3669. Min Act: -0.1700

Data Index: 2412479 (Open Web Text)

Max Activating Token Index: 694

Text #3

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2936. Min Act: -0.1700

Data Index: 3853658 (Open Web Text)

Max Activating Token Index: 747

Text #4

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.3569. Min Act: -0.1700

Data Index: 8455950 (Open Web Text)

Max Activating Token Index: 752

Text #5

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.3174. Min Act: -0.1700

Data Index: 130799 (Open Web Text)

Max Activating Token Index: 116

Text #6

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.3063. Min Act: -0.1700

Data Index: 137302 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.3105. Min Act: -0.1700

Data Index: 840175 (Open Web Text)

Max Activating Token Index: 304

Text #8

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2970. Min Act: -0.1700

Data Index: 3635240 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2509. Min Act: -0.1700

Data Index: 7780210 (Open Web Text)

Max Activating Token Index: 944

Text #10

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2816. Min Act: -0.1700

Data Index: 6262316 (Open Web Text)

Max Activating Token Index: 589

Text #11

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2706. Min Act: -0.1700

Data Index: 3925511 (Open Web Text)

Max Activating Token Index: 348

Text #12

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2021. Min Act: -0.1700

Data Index: 6734874 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2498. Min Act: -0.1700

Data Index: 7735843 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2365. Min Act: -0.1700

Data Index: 7586318 (Open Web Text)

Max Activating Token Index: 100

Text #15

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2592. Min Act: -0.1700

Data Index: 1104791 (Open Web Text)

Max Activating Token Index: 961

Text #16

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2602. Min Act: -0.1700

Data Index: 4944045 (Open Web Text)

Max Activating Token Index: 228

Text #17

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2492. Min Act: -0.1700

Data Index: 3642536 (Open Web Text)

Max Activating Token Index: 773

Text #18

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2690. Min Act: -0.1700

Data Index: 3224629 (Open Web Text)

Max Activating Token Index: 861

Text #19

Max Range: 3.5440. Min Range: -3.5440

Max Act: 3.2015. Min Act: -0.1700

Data Index: 2302830 (Open Web Text)

Max Activating Token Index: 150