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

Dataset: Open Web Text

Neuron 2933 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: 4.8105. Min Range: -4.8105

Max Act: 4.8105. Min Act: -0.1700

Data Index: 1246110 (Open Web Text)

Max Activating Token Index: 122

Text #1

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.7518. Min Act: -0.1700

Data Index: 5705839 (Open Web Text)

Max Activating Token Index: 483

Text #2

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6671. Min Act: -0.1700

Data Index: 6961459 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6958. Min Act: -0.1700

Data Index: 5954778 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6803. Min Act: -0.1700

Data Index: 8314763 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6994. Min Act: -0.1700

Data Index: 5034201 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6866. Min Act: -0.1700

Data Index: 7798247 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6942. Min Act: -0.1700

Data Index: 4457636 (Open Web Text)

Max Activating Token Index: 492

Text #8

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6806. Min Act: -0.1700

Data Index: 2211693 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6825. Min Act: -0.1700

Data Index: 4371297 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6973. Min Act: -0.1700

Data Index: 4200635 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6938. Min Act: -0.1700

Data Index: 1776373 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6701. Min Act: -0.1700

Data Index: 1753258 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6588. Min Act: -0.1700

Data Index: 6118297 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6576. Min Act: -0.1700

Data Index: 4155281 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6945. Min Act: -0.1700

Data Index: 3877255 (Open Web Text)

Max Activating Token Index: 502

Text #16

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6265. Min Act: -0.1700

Data Index: 3531609 (Open Web Text)

Max Activating Token Index: 181

Text #17

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6023. Min Act: -0.1700

Data Index: 2453763 (Open Web Text)

Max Activating Token Index: 148

Text #18

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6337. Min Act: -0.1700

Data Index: 3710240 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 4.8105. Min Range: -4.8105

Max Act: 4.6276. Min Act: -0.1700

Data Index: 3778754 (Open Web Text)

Max Activating Token Index: 483