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

Dataset: Open Web Text

Neuron 2906 in Layer 6

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: 3.7086. Min Range: -3.7086

Max Act: 3.7086. Min Act: -0.1700

Data Index: 3114860 (Open Web Text)

Max Activating Token Index: 568

Text #1

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.5717. Min Act: -0.1700

Data Index: 1091719 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.5358. Min Act: -0.1700

Data Index: 6650620 (Open Web Text)

Max Activating Token Index: 342

Text #3

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.5339. Min Act: -0.1700

Data Index: 4710369 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.5128. Min Act: -0.1700

Data Index: 6714387 (Open Web Text)

Max Activating Token Index: 142

Text #5

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4957. Min Act: -0.1700

Data Index: 758110 (Open Web Text)

Max Activating Token Index: 200

Text #6

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.5092. Min Act: -0.1700

Data Index: 6011537 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.5061. Min Act: -0.1700

Data Index: 1776246 (Open Web Text)

Max Activating Token Index: 644

Text #8

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4909. Min Act: -0.1700

Data Index: 5619145 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4764. Min Act: -0.1700

Data Index: 1262743 (Open Web Text)

Max Activating Token Index: 831

Text #10

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4776. Min Act: -0.1700

Data Index: 1883839 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.5030. Min Act: -0.1700

Data Index: 6776955 (Open Web Text)

Max Activating Token Index: 879

Text #12

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4948. Min Act: -0.1700

Data Index: 804796 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4897. Min Act: -0.1700

Data Index: 4887669 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4643. Min Act: -0.1700

Data Index: 3177781 (Open Web Text)

Max Activating Token Index: 933

Text #15

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4507. Min Act: -0.1700

Data Index: 2896422 (Open Web Text)

Max Activating Token Index: 220

Text #16

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4775. Min Act: -0.1700

Data Index: 2025660 (Open Web Text)

Max Activating Token Index: 874

Text #17

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4774. Min Act: -0.1700

Data Index: 8240179 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4435. Min Act: -0.1700

Data Index: 6189092 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 3.7086. Min Range: -3.7086

Max Act: 3.4416. Min Act: -0.1700

Data Index: 4710357 (Open Web Text)

Max Activating Token Index: 919