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

Dataset: Open Web Text

Neuron 2149 in Layer 0

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: 5.3935. Min Range: -5.3935

Max Act: 5.3935. Min Act: -0.1700

Data Index: 5356035 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.3612. Min Act: -0.1700

Data Index: 7154600 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.3265. Min Act: -0.1700

Data Index: 1131969 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.3017. Min Act: -0.1700

Data Index: 4853605 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2965. Min Act: -0.1700

Data Index: 8814029 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2927. Min Act: -0.1700

Data Index: 294926 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2841. Min Act: -0.1700

Data Index: 260839 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2502. Min Act: -0.1700

Data Index: 416227 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2574. Min Act: -0.1700

Data Index: 2143783 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2648. Min Act: -0.1700

Data Index: 7757481 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2366. Min Act: -0.1700

Data Index: 2517885 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2127. Min Act: -0.1700

Data Index: 2688599 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2301. Min Act: -0.1700

Data Index: 2320082 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2357. Min Act: -0.1700

Data Index: 6934328 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2202. Min Act: -0.1700

Data Index: 8379376 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2303. Min Act: -0.1700

Data Index: 8763284 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2190. Min Act: -0.1700

Data Index: 832428 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2482. Min Act: -0.1700

Data Index: 5529926 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2512. Min Act: -0.1700

Data Index: 2179015 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2307. Min Act: -0.1700

Data Index: 5239598 (Open Web Text)

Max Activating Token Index: 4