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

Dataset: Open Web Text

Neuron 802 in Layer 4

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: 4.4562. Min Range: -4.4562

Max Act: 4.4562. Min Act: -0.1700

Data Index: 2658149 (Open Web Text)

Max Activating Token Index: 121

Text #1

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.3129. Min Act: -0.1700

Data Index: 7680971 (Open Web Text)

Max Activating Token Index: 591

Text #2

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.1897. Min Act: -0.1700

Data Index: 6287569 (Open Web Text)

Max Activating Token Index: 846

Text #3

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.2479. Min Act: -0.1700

Data Index: 2159560 (Open Web Text)

Max Activating Token Index: 72

Text #4

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.1366. Min Act: -0.1700

Data Index: 865495 (Open Web Text)

Max Activating Token Index: 893

Text #5

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.1649. Min Act: -0.1700

Data Index: 946549 (Open Web Text)

Max Activating Token Index: 375

Text #6

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0728. Min Act: -0.1700

Data Index: 6174796 (Open Web Text)

Max Activating Token Index: 379

Text #7

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.1276. Min Act: -0.1700

Data Index: 4778474 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0968. Min Act: -0.1700

Data Index: 3711948 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.1080. Min Act: -0.1700

Data Index: 2293901 (Open Web Text)

Max Activating Token Index: 401

Text #10

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0877. Min Act: -0.1700

Data Index: 7934145 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.1024. Min Act: -0.1700

Data Index: 4509584 (Open Web Text)

Max Activating Token Index: 718

Text #12

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0682. Min Act: -0.1700

Data Index: 5884300 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0170. Min Act: -0.1700

Data Index: 4635692 (Open Web Text)

Max Activating Token Index: 782

Text #14

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0459. Min Act: -0.1700

Data Index: 8043432 (Open Web Text)

Max Activating Token Index: 660

Text #15

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0872. Min Act: -0.1700

Data Index: 3239518 (Open Web Text)

Max Activating Token Index: 625

Text #16

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0251. Min Act: -0.1700

Data Index: 5456527 (Open Web Text)

Max Activating Token Index: 32

Text #17

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0298. Min Act: -0.1700

Data Index: 8613367 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0298. Min Act: -0.1700

Data Index: 5324208 (Open Web Text)

Max Activating Token Index: 132

Text #19

Max Range: 4.4562. Min Range: -4.4562

Max Act: 4.0191. Min Act: -0.1700

Data Index: 4706301 (Open Web Text)

Max Activating Token Index: 501