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

Dataset: Open Web Text

Neuron 127 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: 5.4916. Min Range: -5.4916

Max Act: 5.4916. Min Act: -0.1700

Data Index: 5383717 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.4580. Min Act: -0.1700

Data Index: 3101772 (Open Web Text)

Max Activating Token Index: 402

Text #2

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.4011. Min Act: -0.1700

Data Index: 3644423 (Open Web Text)

Max Activating Token Index: 494

Text #3

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.4058. Min Act: -0.1700

Data Index: 6154306 (Open Web Text)

Max Activating Token Index: 184

Text #4

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.3311. Min Act: -0.1700

Data Index: 1871251 (Open Web Text)

Max Activating Token Index: 767

Text #5

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.3685. Min Act: -0.1700

Data Index: 3316662 (Open Web Text)

Max Activating Token Index: 737

Text #6

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.3745. Min Act: -0.1700

Data Index: 1982748 (Open Web Text)

Max Activating Token Index: 114

Text #7

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.3084. Min Act: -0.1700

Data Index: 5912887 (Open Web Text)

Max Activating Token Index: 980

Text #8

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2579. Min Act: -0.1700

Data Index: 2314138 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2592. Min Act: -0.1700

Data Index: 6231386 (Open Web Text)

Max Activating Token Index: 370

Text #10

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.3193. Min Act: -0.1700

Data Index: 6844948 (Open Web Text)

Max Activating Token Index: 153

Text #11

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2716. Min Act: -0.1700

Data Index: 7139495 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2139. Min Act: -0.1700

Data Index: 5043805 (Open Web Text)

Max Activating Token Index: 848

Text #13

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2297. Min Act: -0.1700

Data Index: 8829886 (Open Web Text)

Max Activating Token Index: 849

Text #14

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2737. Min Act: -0.1700

Data Index: 8558972 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2054. Min Act: -0.1700

Data Index: 3054575 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2003. Min Act: -0.1700

Data Index: 758972 (Open Web Text)

Max Activating Token Index: 922

Text #17

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.1673. Min Act: -0.1700

Data Index: 3362160 (Open Web Text)

Max Activating Token Index: 650

Text #18

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.2125. Min Act: -0.1700

Data Index: 705129 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 5.4916. Min Range: -5.4916

Max Act: 5.1646. Min Act: -0.1700

Data Index: 2274329 (Open Web Text)

Max Activating Token Index: 684