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

Dataset: Open Web Text

Neuron 969 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: 3.6601. Min Range: -3.6601

Max Act: 3.6601. Min Act: -0.1700

Data Index: 2790144 (Open Web Text)

Max Activating Token Index: 156

Text #1

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.4275. Min Act: -0.1700

Data Index: 8548874 (Open Web Text)

Max Activating Token Index: 808

Text #2

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.4467. Min Act: -0.1700

Data Index: 5960348 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3361. Min Act: -0.1700

Data Index: 5999103 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3963. Min Act: -0.1700

Data Index: 4953831 (Open Web Text)

Max Activating Token Index: 308

Text #5

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.4109. Min Act: -0.1700

Data Index: 2128774 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3821. Min Act: -0.1700

Data Index: 4997334 (Open Web Text)

Max Activating Token Index: 847

Text #7

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3567. Min Act: -0.1700

Data Index: 8310261 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3712. Min Act: -0.1700

Data Index: 1462933 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3620. Min Act: -0.1700

Data Index: 2385254 (Open Web Text)

Max Activating Token Index: 906

Text #10

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3679. Min Act: -0.1700

Data Index: 3651814 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3951. Min Act: -0.1700

Data Index: 6856932 (Open Web Text)

Max Activating Token Index: 802

Text #12

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3329. Min Act: -0.1700

Data Index: 2084830 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3074. Min Act: -0.1700

Data Index: 3264509 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3356. Min Act: -0.1700

Data Index: 7783058 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3484. Min Act: -0.1700

Data Index: 5289175 (Open Web Text)

Max Activating Token Index: 36

Text #16

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3133. Min Act: -0.1700

Data Index: 890989 (Open Web Text)

Max Activating Token Index: 832

Text #17

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3229. Min Act: -0.1700

Data Index: 251340 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.3096. Min Act: -0.1700

Data Index: 6020415 (Open Web Text)

Max Activating Token Index: 889

Text #19

Max Range: 3.6601. Min Range: -3.6601

Max Act: 3.2973. Min Act: -0.1700

Data Index: 1961987 (Open Web Text)

Max Activating Token Index: 757