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

Dataset: Open Web Text

Neuron 227 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: 3.2979. Min Range: -3.2979

Max Act: 3.2979. Min Act: -0.1700

Data Index: 5108704 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2403. Min Act: -0.1700

Data Index: 8438758 (Open Web Text)

Max Activating Token Index: 913

Text #2

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2407. Min Act: -0.1700

Data Index: 2216835 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2318. Min Act: -0.1700

Data Index: 6947016 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2318. Min Act: -0.1700

Data Index: 5615570 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2318. Min Act: -0.1700

Data Index: 2531657 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2318. Min Act: -0.1700

Data Index: 3478312 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2318. Min Act: -0.1700

Data Index: 3525720 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2318. Min Act: -0.1700

Data Index: 5903411 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2318. Min Act: -0.1700

Data Index: 1362235 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2381. Min Act: -0.1700

Data Index: 6469912 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2318. Min Act: -0.1700

Data Index: 8560750 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2180. Min Act: -0.1700

Data Index: 1825557 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2225. Min Act: -0.1700

Data Index: 4281771 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2218. Min Act: -0.1700

Data Index: 798063 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2226. Min Act: -0.1700

Data Index: 3856392 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2242. Min Act: -0.1700

Data Index: 5534409 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2016. Min Act: -0.1700

Data Index: 155360 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2086. Min Act: -0.1700

Data Index: 4349010 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.2979. Min Range: -3.2979

Max Act: 3.2114. Min Act: -0.1700

Data Index: 2444727 (Open Web Text)

Max Activating Token Index: 3