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

Dataset: Open Web Text

Neuron 1399 in Layer 3

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: 4.5856. Min Range: -4.5856

Max Act: 4.5856. Min Act: -0.1700

Data Index: 8481322 (Open Web Text)

Max Activating Token Index: 137

Text #1

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.4756. Min Act: -0.1700

Data Index: 5752291 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.4500. Min Act: -0.1700

Data Index: 6268429 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.4686. Min Act: -0.1700

Data Index: 4539580 (Open Web Text)

Max Activating Token Index: 80

Text #4

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.3960. Min Act: -0.1700

Data Index: 6529807 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.3439. Min Act: -0.1700

Data Index: 232685 (Open Web Text)

Max Activating Token Index: 898

Text #6

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.3399. Min Act: -0.1700

Data Index: 3448268 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.3355. Min Act: -0.1700

Data Index: 6232525 (Open Web Text)

Max Activating Token Index: 98

Text #8

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.3416. Min Act: -0.1700

Data Index: 4386413 (Open Web Text)

Max Activating Token Index: 64

Text #9

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.3245. Min Act: -0.1700

Data Index: 4100159 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.3083. Min Act: -0.1700

Data Index: 5777544 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2746. Min Act: -0.1700

Data Index: 7250215 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2902. Min Act: -0.1700

Data Index: 3760919 (Open Web Text)

Max Activating Token Index: 470

Text #13

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2903. Min Act: -0.1700

Data Index: 7429280 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2564. Min Act: -0.1700

Data Index: 5984641 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2755. Min Act: -0.1700

Data Index: 5045826 (Open Web Text)

Max Activating Token Index: 231

Text #16

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2528. Min Act: -0.1700

Data Index: 7613647 (Open Web Text)

Max Activating Token Index: 956

Text #17

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2606. Min Act: -0.1700

Data Index: 3579585 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2450. Min Act: -0.1700

Data Index: 793739 (Open Web Text)

Max Activating Token Index: 457

Text #19

Max Range: 4.5856. Min Range: -4.5856

Max Act: 4.2615. Min Act: -0.1700

Data Index: 158078 (Open Web Text)

Max Activating Token Index: 484