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

Dataset: Open Web Text

Neuron 2406 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: 3.0913. Min Range: -3.0913

Max Act: 3.0913. Min Act: -0.1700

Data Index: 5766097 (Open Web Text)

Max Activating Token Index: 373

Text #1

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0578. Min Act: -0.1700

Data Index: 4761905 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 3.0913. Min Range: -3.0913

Max Act: 3.0399. Min Act: -0.1700

Data Index: 4756029 (Open Web Text)

Max Activating Token Index: 135

Text #3

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9976. Min Act: -0.1700

Data Index: 3443600 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9568. Min Act: -0.1700

Data Index: 2677002 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9540. Min Act: -0.1700

Data Index: 5766095 (Open Web Text)

Max Activating Token Index: 525

Text #6

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9484. Min Act: -0.1700

Data Index: 7117152 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9498. Min Act: -0.1700

Data Index: 125559 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9462. Min Act: -0.1700

Data Index: 1785931 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.8965. Min Act: -0.1700

Data Index: 4832265 (Open Web Text)

Max Activating Token Index: 899

Text #10

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9162. Min Act: -0.1700

Data Index: 6211469 (Open Web Text)

Max Activating Token Index: 838

Text #11

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9266. Min Act: -0.1700

Data Index: 8313142 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9324. Min Act: -0.1700

Data Index: 1140555 (Open Web Text)

Max Activating Token Index: 383

Text #13

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9304. Min Act: -0.1700

Data Index: 3443599 (Open Web Text)

Max Activating Token Index: 90

Text #14

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9375. Min Act: -0.1700

Data Index: 3467380 (Open Web Text)

Max Activating Token Index: 633

Text #15

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.8942. Min Act: -0.1700

Data Index: 8723953 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9211. Min Act: -0.1700

Data Index: 5555736 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9303. Min Act: -0.1700

Data Index: 5193931 (Open Web Text)

Max Activating Token Index: 999

Text #18

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9000. Min Act: -0.1700

Data Index: 6032989 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 3.0913. Min Range: -3.0913

Max Act: 2.9185. Min Act: -0.1700

Data Index: 3228242 (Open Web Text)

Max Activating Token Index: 100