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

Dataset: Open Web Text

Neuron 1468 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: 4.4624. Min Range: -4.4624

Max Act: 4.4624. Min Act: -0.1700

Data Index: 54717 (Open Web Text)

Max Activating Token Index: 761

Text #1

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.4145. Min Act: -0.1700

Data Index: 1388882 (Open Web Text)

Max Activating Token Index: 175

Text #2

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3840. Min Act: -0.1700

Data Index: 4548102 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3680. Min Act: -0.1700

Data Index: 3307501 (Open Web Text)

Max Activating Token Index: 493

Text #4

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3864. Min Act: -0.1700

Data Index: 7322056 (Open Web Text)

Max Activating Token Index: 658

Text #5

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3822. Min Act: -0.1700

Data Index: 7326328 (Open Web Text)

Max Activating Token Index: 590

Text #6

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3590. Min Act: -0.1700

Data Index: 1948505 (Open Web Text)

Max Activating Token Index: 537

Text #7

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3043. Min Act: -0.1700

Data Index: 8631606 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3610. Min Act: -0.1700

Data Index: 2626310 (Open Web Text)

Max Activating Token Index: 382

Text #9

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3796. Min Act: -0.1700

Data Index: 8204921 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3662. Min Act: -0.1700

Data Index: 2249814 (Open Web Text)

Max Activating Token Index: 271

Text #11

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3356. Min Act: -0.1700

Data Index: 4995590 (Open Web Text)

Max Activating Token Index: 966

Text #12

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3133. Min Act: -0.1700

Data Index: 7602097 (Open Web Text)

Max Activating Token Index: 659

Text #13

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3432. Min Act: -0.1700

Data Index: 595658 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3007. Min Act: -0.1700

Data Index: 7445945 (Open Web Text)

Max Activating Token Index: 254

Text #15

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3124. Min Act: -0.1700

Data Index: 3540076 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3251. Min Act: -0.1700

Data Index: 511782 (Open Web Text)

Max Activating Token Index: 548

Text #17

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2906. Min Act: -0.1700

Data Index: 387764 (Open Web Text)

Max Activating Token Index: 345

Text #18

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3118. Min Act: -0.1700

Data Index: 4630459 (Open Web Text)

Max Activating Token Index: 953

Text #19

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.3163. Min Act: -0.1700

Data Index: 6609202 (Open Web Text)

Max Activating Token Index: 617