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

Dataset: Open Web Text

Neuron 2096 in Layer 6

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: 5.1842. Min Range: -5.1842

Max Act: 5.1842. Min Act: -0.1700

Data Index: 251352 (Open Web Text)

Max Activating Token Index: 135

Text #1

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.8204. Min Act: -0.1700

Data Index: 7073069 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.7690. Min Act: -0.1700

Data Index: 4551747 (Open Web Text)

Max Activating Token Index: 884

Text #3

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.7471. Min Act: -0.1700

Data Index: 3892646 (Open Web Text)

Max Activating Token Index: 116

Text #4

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.7245. Min Act: -0.1700

Data Index: 7607191 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.7276. Min Act: -0.1700

Data Index: 6384158 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.6844. Min Act: -0.1700

Data Index: 2376127 (Open Web Text)

Max Activating Token Index: 34

Text #7

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.6230. Min Act: -0.1700

Data Index: 7006092 (Open Web Text)

Max Activating Token Index: 899

Text #8

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.6488. Min Act: -0.1700

Data Index: 7057239 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.6184. Min Act: -0.1700

Data Index: 2783163 (Open Web Text)

Max Activating Token Index: 215

Text #10

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.6031. Min Act: -0.1700

Data Index: 1445740 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.6104. Min Act: -0.1700

Data Index: 2376120 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.5903. Min Act: -0.1700

Data Index: 1676807 (Open Web Text)

Max Activating Token Index: 675

Text #13

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.5943. Min Act: -0.1700

Data Index: 105094 (Open Web Text)

Max Activating Token Index: 176

Text #14

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.6017. Min Act: -0.1700

Data Index: 4998286 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.5425. Min Act: -0.1700

Data Index: 5147219 (Open Web Text)

Max Activating Token Index: 284

Text #16

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.5784. Min Act: -0.1700

Data Index: 3148543 (Open Web Text)

Max Activating Token Index: 407

Text #17

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.5242. Min Act: -0.1700

Data Index: 1910356 (Open Web Text)

Max Activating Token Index: 857

Text #18

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.5044. Min Act: -0.1700

Data Index: 2876994 (Open Web Text)

Max Activating Token Index: 229

Text #19

Max Range: 5.1842. Min Range: -5.1842

Max Act: 4.4973. Min Act: -0.1700

Data Index: 4350698 (Open Web Text)

Max Activating Token Index: 861