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

Dataset: Open Web Text

Neuron 1197 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: 4.4952. Min Range: -4.4952

Max Act: 4.4952. Min Act: -0.1700

Data Index: 2412479 (Open Web Text)

Max Activating Token Index: 680

Text #1

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4303. Min Act: -0.1700

Data Index: 7228776 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4313. Min Act: -0.1700

Data Index: 2054026 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4114. Min Act: -0.1700

Data Index: 1482535 (Open Web Text)

Max Activating Token Index: 221

Text #4

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.4175. Min Act: -0.1700

Data Index: 25073 (Open Web Text)

Max Activating Token Index: 328

Text #5

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3455. Min Act: -0.1700

Data Index: 3067380 (Open Web Text)

Max Activating Token Index: 762

Text #6

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3636. Min Act: -0.1700

Data Index: 2564676 (Open Web Text)

Max Activating Token Index: 586

Text #7

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3437. Min Act: -0.1700

Data Index: 5939815 (Open Web Text)

Max Activating Token Index: 742

Text #8

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3463. Min Act: -0.1700

Data Index: 6079552 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3556. Min Act: -0.1700

Data Index: 3941115 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3202. Min Act: -0.1700

Data Index: 3941114 (Open Web Text)

Max Activating Token Index: 754

Text #11

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.3276. Min Act: -0.1700

Data Index: 7719638 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.2624. Min Act: -0.1700

Data Index: 5545739 (Open Web Text)

Max Activating Token Index: 899

Text #13

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.2221. Min Act: -0.1700

Data Index: 2834129 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.2601. Min Act: -0.1700

Data Index: 8602187 (Open Web Text)

Max Activating Token Index: 169

Text #15

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.2815. Min Act: -0.1700

Data Index: 7392191 (Open Web Text)

Max Activating Token Index: 94

Text #16

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.2734. Min Act: -0.1700

Data Index: 4154721 (Open Web Text)

Max Activating Token Index: 921

Text #17

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.2385. Min Act: -0.1700

Data Index: 3403196 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.2467. Min Act: -0.1700

Data Index: 6071783 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 4.4952. Min Range: -4.4952

Max Act: 4.2519. Min Act: -0.1700

Data Index: 1743475 (Open Web Text)

Max Activating Token Index: 901