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

Dataset: Open Web Text

Neuron 138 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: 4.8079. Min Range: -4.8079

Max Act: 4.8039. Min Act: -0.1700

Data Index: 3794705 (Open Web Text)

Max Activating Token Index: 201

Text #1

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.8079. Min Act: -0.1700

Data Index: 5395207 (Open Web Text)

Max Activating Token Index: 980

Text #2

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.6802. Min Act: -0.1700

Data Index: 6443305 (Open Web Text)

Max Activating Token Index: 867

Text #3

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.6733. Min Act: -0.1700

Data Index: 8307773 (Open Web Text)

Max Activating Token Index: 176

Text #4

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.7227. Min Act: -0.1700

Data Index: 6172445 (Open Web Text)

Max Activating Token Index: 626

Text #5

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.6625. Min Act: -0.1700

Data Index: 6881374 (Open Web Text)

Max Activating Token Index: 835

Text #6

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.6803. Min Act: -0.1700

Data Index: 8157165 (Open Web Text)

Max Activating Token Index: 122

Text #7

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.6505. Min Act: -0.1700

Data Index: 131127 (Open Web Text)

Max Activating Token Index: 991

Text #8

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.6467. Min Act: -0.1700

Data Index: 8555140 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5589. Min Act: -0.1700

Data Index: 661069 (Open Web Text)

Max Activating Token Index: 873

Text #10

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5723. Min Act: -0.1700

Data Index: 7149756 (Open Web Text)

Max Activating Token Index: 98

Text #11

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5806. Min Act: -0.1700

Data Index: 3443972 (Open Web Text)

Max Activating Token Index: 1002

Text #12

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.6105. Min Act: -0.1700

Data Index: 4960021 (Open Web Text)

Max Activating Token Index: 950

Text #13

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5997. Min Act: -0.1700

Data Index: 255258 (Open Web Text)

Max Activating Token Index: 99

Text #14

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5612. Min Act: -0.1700

Data Index: 7840366 (Open Web Text)

Max Activating Token Index: 438

Text #15

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5170. Min Act: -0.1700

Data Index: 5862143 (Open Web Text)

Max Activating Token Index: 895

Text #16

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5360. Min Act: -0.1700

Data Index: 886379 (Open Web Text)

Max Activating Token Index: 757

Text #17

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5503. Min Act: -0.1700

Data Index: 7661640 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5509. Min Act: -0.1700

Data Index: 7108478 (Open Web Text)

Max Activating Token Index: 186

Text #19

Max Range: 4.8079. Min Range: -4.8079

Max Act: 4.5832. Min Act: -0.1700

Data Index: 1905567 (Open Web Text)

Max Activating Token Index: 785