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

Dataset: Open Web Text

Neuron 2859 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: 3.8942. Min Range: -3.8942

Max Act: 3.8942. Min Act: -0.1700

Data Index: 1366438 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8143. Min Act: -0.1700

Data Index: 8660340 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7931. Min Act: -0.1700

Data Index: 6311554 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7557. Min Act: -0.1700

Data Index: 5016156 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7581. Min Act: -0.1700

Data Index: 2997313 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7525. Min Act: -0.1700

Data Index: 2001147 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7504. Min Act: -0.1700

Data Index: 3024302 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7527. Min Act: -0.1700

Data Index: 3302344 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7283. Min Act: -0.1700

Data Index: 4383791 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7257. Min Act: -0.1700

Data Index: 1951465 (Open Web Text)

Max Activating Token Index: 33

Text #10

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7204. Min Act: -0.1700

Data Index: 1944239 (Open Web Text)

Max Activating Token Index: 962

Text #11

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7217. Min Act: -0.1700

Data Index: 6054429 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7400. Min Act: -0.1700

Data Index: 267449 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7299. Min Act: -0.1700

Data Index: 273256 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7421. Min Act: -0.1700

Data Index: 1764954 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7395. Min Act: -0.1700

Data Index: 3087781 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7134. Min Act: -0.1700

Data Index: 2146237 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7238. Min Act: -0.1700

Data Index: 2107167 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7276. Min Act: -0.1700

Data Index: 5672050 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7371. Min Act: -0.1700

Data Index: 537391 (Open Web Text)

Max Activating Token Index: 6