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

Dataset: Open Web Text

Neuron 1108 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: 4.2520. Min Range: -4.2520

Max Act: 4.2520. Min Act: -0.1700

Data Index: 8243109 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.2165. Min Act: -0.1700

Data Index: 1708465 (Open Web Text)

Max Activating Token Index: 841

Text #2

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.1222. Min Act: -0.1700

Data Index: 6786818 (Open Web Text)

Max Activating Token Index: 677

Text #3

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.1990. Min Act: -0.1700

Data Index: 7595292 (Open Web Text)

Max Activating Token Index: 564

Text #4

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.0737. Min Act: -0.1700

Data Index: 952177 (Open Web Text)

Max Activating Token Index: 423

Text #5

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.0827. Min Act: -0.1700

Data Index: 2984105 (Open Web Text)

Max Activating Token Index: 476

Text #6

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.0523. Min Act: -0.1700

Data Index: 6248484 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.0465. Min Act: -0.1700

Data Index: 5570801 (Open Web Text)

Max Activating Token Index: 806

Text #8

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.9759. Min Act: -0.1700

Data Index: 7441280 (Open Web Text)

Max Activating Token Index: 199

Text #9

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.0138. Min Act: -0.1700

Data Index: 2045517 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.0253. Min Act: -0.1700

Data Index: 3008449 (Open Web Text)

Max Activating Token Index: 437

Text #11

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.9833. Min Act: -0.1700

Data Index: 4592013 (Open Web Text)

Max Activating Token Index: 763

Text #12

Max Range: 4.2520. Min Range: -4.2520

Max Act: 4.0485. Min Act: -0.1700

Data Index: 1909938 (Open Web Text)

Max Activating Token Index: 760

Text #13

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.9961. Min Act: -0.1700

Data Index: 4706153 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.9162. Min Act: -0.1700

Data Index: 5808852 (Open Web Text)

Max Activating Token Index: 913

Text #15

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.9960. Min Act: -0.1700

Data Index: 498522 (Open Web Text)

Max Activating Token Index: 919

Text #16

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.9575. Min Act: -0.1700

Data Index: 6202747 (Open Web Text)

Max Activating Token Index: 994

Text #17

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.8731. Min Act: -0.1700

Data Index: 628976 (Open Web Text)

Max Activating Token Index: 575

Text #18

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.9599. Min Act: -0.1700

Data Index: 532552 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 4.2520. Min Range: -4.2520

Max Act: 3.8860. Min Act: -0.1700

Data Index: 2161541 (Open Web Text)

Max Activating Token Index: 574