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

Dataset: Open Web Text

Neuron 637 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: 2.2148. Min Range: -2.2148

Max Act: 2.2148. Min Act: -0.1700

Data Index: 3490678 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.9905. Min Act: -0.1700

Data Index: 3335548 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.8530. Min Act: -0.1700

Data Index: 8369827 (Open Web Text)

Max Activating Token Index: 147

Text #3

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.8266. Min Act: -0.1700

Data Index: 6357875 (Open Web Text)

Max Activating Token Index: 670

Text #4

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.8205. Min Act: -0.1700

Data Index: 6357876 (Open Web Text)

Max Activating Token Index: 225

Text #5

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.7881. Min Act: -0.1700

Data Index: 1223419 (Open Web Text)

Max Activating Token Index: 1021

Text #6

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.7605. Min Act: -0.1700

Data Index: 1223420 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.7339. Min Act: -0.1700

Data Index: 4405050 (Open Web Text)

Max Activating Token Index: 1019

Text #8

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.7163. Min Act: -0.1700

Data Index: 7874089 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.7025. Min Act: -0.1700

Data Index: 864592 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6644. Min Act: -0.1700

Data Index: 8065595 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6767. Min Act: -0.1700

Data Index: 4405051 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6704. Min Act: -0.1700

Data Index: 2045641 (Open Web Text)

Max Activating Token Index: 711

Text #13

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6465. Min Act: -0.1700

Data Index: 777380 (Open Web Text)

Max Activating Token Index: 559

Text #14

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6354. Min Act: -0.1700

Data Index: 8192616 (Open Web Text)

Max Activating Token Index: 95

Text #15

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6332. Min Act: -0.1700

Data Index: 4903588 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6194. Min Act: -0.1700

Data Index: 4996615 (Open Web Text)

Max Activating Token Index: 688

Text #17

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6295. Min Act: -0.1700

Data Index: 6615565 (Open Web Text)

Max Activating Token Index: 27

Text #18

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6124. Min Act: -0.1700

Data Index: 1251405 (Open Web Text)

Max Activating Token Index: 52

Text #19

Max Range: 2.2148. Min Range: -2.2148

Max Act: 1.6150. Min Act: -0.1700

Data Index: 7195791 (Open Web Text)

Max Activating Token Index: 18