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

Dataset: Open Web Text

Neuron 2584 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: 4.7533. Min Range: -4.7533

Max Act: 4.7533. Min Act: -0.1700

Data Index: 7324553 (Open Web Text)

Max Activating Token Index: 88

Text #1

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.7304. Min Act: -0.1700

Data Index: 7649846 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.6708. Min Act: -0.1700

Data Index: 7092701 (Open Web Text)

Max Activating Token Index: 261

Text #3

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.6622. Min Act: -0.1700

Data Index: 6755677 (Open Web Text)

Max Activating Token Index: 761

Text #4

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.6158. Min Act: -0.1700

Data Index: 581866 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.6517. Min Act: -0.1700

Data Index: 7649852 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.6473. Min Act: -0.1700

Data Index: 651914 (Open Web Text)

Max Activating Token Index: 198

Text #7

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.6160. Min Act: -0.1700

Data Index: 6755665 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.5540. Min Act: -0.1700

Data Index: 7308983 (Open Web Text)

Max Activating Token Index: 373

Text #9

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.5239. Min Act: -0.1700

Data Index: 6544710 (Open Web Text)

Max Activating Token Index: 784

Text #10

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.5469. Min Act: -0.1700

Data Index: 2075241 (Open Web Text)

Max Activating Token Index: 167

Text #11

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.5347. Min Act: -0.1700

Data Index: 8440948 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.4972. Min Act: -0.1700

Data Index: 8001976 (Open Web Text)

Max Activating Token Index: 410

Text #13

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.5143. Min Act: -0.1700

Data Index: 6441202 (Open Web Text)

Max Activating Token Index: 291

Text #14

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.4414. Min Act: -0.1700

Data Index: 671759 (Open Web Text)

Max Activating Token Index: 592

Text #15

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.4497. Min Act: -0.1700

Data Index: 3411021 (Open Web Text)

Max Activating Token Index: 398

Text #16

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.4279. Min Act: -0.1700

Data Index: 7883093 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.4696. Min Act: -0.1700

Data Index: 3055593 (Open Web Text)

Max Activating Token Index: 826

Text #18

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.4673. Min Act: -0.1700

Data Index: 6412134 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 4.7533. Min Range: -4.7533

Max Act: 4.4325. Min Act: -0.1700

Data Index: 5418986 (Open Web Text)

Max Activating Token Index: 667