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

Dataset: Open Web Text

Neuron 2139 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: 2.8224. Min Range: -2.8224

Max Act: 2.8171. Min Act: -0.1700

Data Index: 8753933 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.8004. Min Act: -0.1700

Data Index: 2230571 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.8224. Min Act: -0.1700

Data Index: 4132522 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7949. Min Act: -0.1700

Data Index: 2669999 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7949. Min Act: -0.1700

Data Index: 6728918 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7732. Min Act: -0.1700

Data Index: 7372593 (Open Web Text)

Max Activating Token Index: 40

Text #6

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7728. Min Act: -0.1700

Data Index: 4281808 (Open Web Text)

Max Activating Token Index: 75

Text #7

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7493. Min Act: -0.1700

Data Index: 4854048 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7567. Min Act: -0.1700

Data Index: 368078 (Open Web Text)

Max Activating Token Index: 61

Text #9

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7677. Min Act: -0.1700

Data Index: 5731690 (Open Web Text)

Max Activating Token Index: 53

Text #10

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7478. Min Act: -0.1700

Data Index: 1937106 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7289. Min Act: -0.1700

Data Index: 3002860 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7397. Min Act: -0.1700

Data Index: 5598312 (Open Web Text)

Max Activating Token Index: 65

Text #13

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7283. Min Act: -0.1700

Data Index: 1265490 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7524. Min Act: -0.1700

Data Index: 4424283 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7520. Min Act: -0.1700

Data Index: 941271 (Open Web Text)

Max Activating Token Index: 85

Text #16

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7468. Min Act: -0.1700

Data Index: 7370107 (Open Web Text)

Max Activating Token Index: 450

Text #17

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7401. Min Act: -0.1700

Data Index: 5410251 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7457. Min Act: -0.1700

Data Index: 450465 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 2.8224. Min Range: -2.8224

Max Act: 2.7379. Min Act: -0.1700

Data Index: 7429506 (Open Web Text)

Max Activating Token Index: 51