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

Dataset: Open Web Text

Neuron 1844 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: 3.1934. Min Range: -3.1934

Max Act: 3.1934. Min Act: -0.1700

Data Index: 412830 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.1493. Min Act: -0.1700

Data Index: 440196 (Open Web Text)

Max Activating Token Index: 752

Text #2

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.1405. Min Act: -0.1700

Data Index: 540762 (Open Web Text)

Max Activating Token Index: 101

Text #3

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.1123. Min Act: -0.1700

Data Index: 2103903 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.1024. Min Act: -0.1700

Data Index: 4202090 (Open Web Text)

Max Activating Token Index: 862

Text #5

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0505. Min Act: -0.1700

Data Index: 5420102 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.1015. Min Act: -0.1700

Data Index: 6861424 (Open Web Text)

Max Activating Token Index: 479

Text #7

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0622. Min Act: -0.1700

Data Index: 5341652 (Open Web Text)

Max Activating Token Index: 241

Text #8

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0658. Min Act: -0.1700

Data Index: 2408479 (Open Web Text)

Max Activating Token Index: 763

Text #9

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0437. Min Act: -0.1700

Data Index: 7416943 (Open Web Text)

Max Activating Token Index: 212

Text #10

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0676. Min Act: -0.1700

Data Index: 8394036 (Open Web Text)

Max Activating Token Index: 858

Text #11

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0289. Min Act: -0.1700

Data Index: 7885755 (Open Web Text)

Max Activating Token Index: 828

Text #12

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0573. Min Act: -0.1700

Data Index: 5354702 (Open Web Text)

Max Activating Token Index: 717

Text #13

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0510. Min Act: -0.1700

Data Index: 1248099 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0595. Min Act: -0.1700

Data Index: 7804157 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0086. Min Act: -0.1700

Data Index: 8317997 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0366. Min Act: -0.1700

Data Index: 3702500 (Open Web Text)

Max Activating Token Index: 270

Text #17

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0462. Min Act: -0.1700

Data Index: 2583012 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0533. Min Act: -0.1700

Data Index: 2812252 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 3.1934. Min Range: -3.1934

Max Act: 3.0218. Min Act: -0.1700

Data Index: 3770627 (Open Web Text)

Max Activating Token Index: 233