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

Dataset: Open Web Text

Neuron 145 in Layer 2

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: 2.7453. Min Range: -2.7453

Max Act: 2.7453. Min Act: -0.1700

Data Index: 6150842 (Open Web Text)

Max Activating Token Index: 796

Text #1

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6512. Min Act: -0.1700

Data Index: 5887996 (Open Web Text)

Max Activating Token Index: 798

Text #2

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6275. Min Act: -0.1700

Data Index: 7995656 (Open Web Text)

Max Activating Token Index: 826

Text #3

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6324. Min Act: -0.1700

Data Index: 5888002 (Open Web Text)

Max Activating Token Index: 691

Text #4

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6249. Min Act: -0.1700

Data Index: 5276179 (Open Web Text)

Max Activating Token Index: 327

Text #5

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6178. Min Act: -0.1700

Data Index: 80521 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6104. Min Act: -0.1700

Data Index: 8732221 (Open Web Text)

Max Activating Token Index: 126

Text #7

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6070. Min Act: -0.1700

Data Index: 5887994 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6062. Min Act: -0.1700

Data Index: 2479583 (Open Web Text)

Max Activating Token Index: 510

Text #9

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5865. Min Act: -0.1700

Data Index: 4010537 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5954. Min Act: -0.1700

Data Index: 2553457 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5833. Min Act: -0.1700

Data Index: 1972776 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5910. Min Act: -0.1700

Data Index: 614880 (Open Web Text)

Max Activating Token Index: 369

Text #13

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5892. Min Act: -0.1700

Data Index: 5887998 (Open Web Text)

Max Activating Token Index: 856

Text #14

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5801. Min Act: -0.1700

Data Index: 1645134 (Open Web Text)

Max Activating Token Index: 470

Text #15

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5883. Min Act: -0.1700

Data Index: 5482579 (Open Web Text)

Max Activating Token Index: 196

Text #16

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5847. Min Act: -0.1700

Data Index: 8490861 (Open Web Text)

Max Activating Token Index: 705

Text #17

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5764. Min Act: -0.1700

Data Index: 7995654 (Open Web Text)

Max Activating Token Index: 560

Text #18

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5689. Min Act: -0.1700

Data Index: 4616046 (Open Web Text)

Max Activating Token Index: 773

Text #19

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5645. Min Act: -0.1700

Data Index: 6561289 (Open Web Text)

Max Activating Token Index: 879