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

Dataset: Open Web Text

Neuron 2858 in Layer 5

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: 3.1809. Min Range: -3.1809

Max Act: 3.1809. Min Act: -0.1700

Data Index: 2827035 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.1048. Min Act: -0.1700

Data Index: 4826296 (Open Web Text)

Max Activating Token Index: 188

Text #2

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.1063. Min Act: -0.1700

Data Index: 88180 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0953. Min Act: -0.1700

Data Index: 7793078 (Open Web Text)

Max Activating Token Index: 261

Text #4

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0907. Min Act: -0.1700

Data Index: 3315888 (Open Web Text)

Max Activating Token Index: 999

Text #5

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0632. Min Act: -0.1700

Data Index: 1910331 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0621. Min Act: -0.1700

Data Index: 2804548 (Open Web Text)

Max Activating Token Index: 159

Text #7

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0791. Min Act: -0.1700

Data Index: 4470023 (Open Web Text)

Max Activating Token Index: 606

Text #8

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0633. Min Act: -0.1700

Data Index: 2745480 (Open Web Text)

Max Activating Token Index: 993

Text #9

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0503. Min Act: -0.1700

Data Index: 3577848 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0398. Min Act: -0.1700

Data Index: 7970007 (Open Web Text)

Max Activating Token Index: 401

Text #11

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0069. Min Act: -0.1700

Data Index: 2871917 (Open Web Text)

Max Activating Token Index: 731

Text #12

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0167. Min Act: -0.1700

Data Index: 6260937 (Open Web Text)

Max Activating Token Index: 545

Text #13

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0443. Min Act: -0.1700

Data Index: 3919507 (Open Web Text)

Max Activating Token Index: 907

Text #14

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0133. Min Act: -0.1700

Data Index: 41074 (Open Web Text)

Max Activating Token Index: 255

Text #15

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0240. Min Act: -0.1700

Data Index: 6271485 (Open Web Text)

Max Activating Token Index: 270

Text #16

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0448. Min Act: -0.1700

Data Index: 1121234 (Open Web Text)

Max Activating Token Index: 433

Text #17

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0124. Min Act: -0.1700

Data Index: 5945578 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 3.1809. Min Range: -3.1809

Max Act: 3.0363. Min Act: -0.1700

Data Index: 5387383 (Open Web Text)

Max Activating Token Index: 152

Text #19

Max Range: 3.1809. Min Range: -3.1809

Max Act: 2.9986. Min Act: -0.1700

Data Index: 2805563 (Open Web Text)

Max Activating Token Index: 819