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

Dataset: Open Web Text

Neuron 2098 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: 6.0053. Min Range: -6.0053

Max Act: 6.0053. Min Act: -0.1700

Data Index: 3218853 (Open Web Text)

Max Activating Token Index: 604

Text #1

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.6004. Min Act: -0.1700

Data Index: 2426538 (Open Web Text)

Max Activating Token Index: 350

Text #2

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.5145. Min Act: -0.1700

Data Index: 3739929 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.5957. Min Act: -0.1700

Data Index: 5466956 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.4111. Min Act: -0.1700

Data Index: 3002735 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.4758. Min Act: -0.1700

Data Index: 2585648 (Open Web Text)

Max Activating Token Index: 774

Text #6

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.2615. Min Act: -0.1700

Data Index: 3440824 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.2245. Min Act: -0.1700

Data Index: 5207945 (Open Web Text)

Max Activating Token Index: 482

Text #8

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.1780. Min Act: -0.1700

Data Index: 8454333 (Open Web Text)

Max Activating Token Index: 98

Text #9

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.1393. Min Act: -0.1700

Data Index: 2241963 (Open Web Text)

Max Activating Token Index: 29

Text #10

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.0724. Min Act: -0.1700

Data Index: 3200452 (Open Web Text)

Max Activating Token Index: 552

Text #11

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.0571. Min Act: -0.1700

Data Index: 439794 (Open Web Text)

Max Activating Token Index: 829

Text #12

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.0536. Min Act: -0.1700

Data Index: 4549964 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.0891. Min Act: -0.1700

Data Index: 1099 (Open Web Text)

Max Activating Token Index: 99

Text #14

Max Range: 6.0053. Min Range: -6.0053

Max Act: 4.9434. Min Act: -0.1700

Data Index: 573169 (Open Web Text)

Max Activating Token Index: 209

Text #15

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.0329. Min Act: -0.1700

Data Index: 2496073 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 6.0053. Min Range: -6.0053

Max Act: 4.9942. Min Act: -0.1700

Data Index: 7270347 (Open Web Text)

Max Activating Token Index: 257

Text #17

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.0293. Min Act: -0.1700

Data Index: 5885202 (Open Web Text)

Max Activating Token Index: 414

Text #18

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.0569. Min Act: -0.1700

Data Index: 5867605 (Open Web Text)

Max Activating Token Index: 197

Text #19

Max Range: 6.0053. Min Range: -6.0053

Max Act: 5.0147. Min Act: -0.1700

Data Index: 7511992 (Open Web Text)

Max Activating Token Index: 307