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

Dataset: Open Web Text

Neuron 2464 in Layer 1

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: 1.8552. Min Range: -1.8552

Max Act: 1.8552. Min Act: -0.1700

Data Index: 7603424 (Open Web Text)

Max Activating Token Index: 158

Text #1

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.8425. Min Act: -0.1700

Data Index: 3294265 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.8139. Min Act: -0.1700

Data Index: 7541666 (Open Web Text)

Max Activating Token Index: 320

Text #3

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.8139. Min Act: -0.1700

Data Index: 17959 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7890. Min Act: -0.1700

Data Index: 707077 (Open Web Text)

Max Activating Token Index: 279

Text #5

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7830. Min Act: -0.1700

Data Index: 196743 (Open Web Text)

Max Activating Token Index: 278

Text #6

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7649. Min Act: -0.1700

Data Index: 6252186 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7713. Min Act: -0.1700

Data Index: 4341119 (Open Web Text)

Max Activating Token Index: 993

Text #8

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7660. Min Act: -0.1700

Data Index: 1425419 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7613. Min Act: -0.1700

Data Index: 3848891 (Open Web Text)

Max Activating Token Index: 231

Text #10

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7637. Min Act: -0.1700

Data Index: 3848892 (Open Web Text)

Max Activating Token Index: 772

Text #11

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7560. Min Act: -0.1700

Data Index: 4040131 (Open Web Text)

Max Activating Token Index: 991

Text #12

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7713. Min Act: -0.1700

Data Index: 3811578 (Open Web Text)

Max Activating Token Index: 802

Text #13

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7533. Min Act: -0.1700

Data Index: 1075878 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7583. Min Act: -0.1700

Data Index: 1768390 (Open Web Text)

Max Activating Token Index: 189

Text #15

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7482. Min Act: -0.1700

Data Index: 8669359 (Open Web Text)

Max Activating Token Index: 813

Text #16

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7456. Min Act: -0.1700

Data Index: 4004204 (Open Web Text)

Max Activating Token Index: 802

Text #17

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7335. Min Act: -0.1700

Data Index: 2898117 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7354. Min Act: -0.1700

Data Index: 4042654 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7374. Min Act: -0.1700

Data Index: 5374835 (Open Web Text)

Max Activating Token Index: 260