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

Dataset: Open Web Text

Neuron 2155 in Layer 1

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: 1.6794. Min Range: -1.6794

Max Act: 1.6794. Min Act: -0.1700

Data Index: 3351764 (Open Web Text)

Max Activating Token Index: 582

Text #1

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6580. Min Act: -0.1700

Data Index: 2520766 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6277. Min Act: -0.1700

Data Index: 484022 (Open Web Text)

Max Activating Token Index: 792

Text #3

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6184. Min Act: -0.1700

Data Index: 8389434 (Open Web Text)

Max Activating Token Index: 523

Text #4

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6199. Min Act: -0.1700

Data Index: 2090132 (Open Web Text)

Max Activating Token Index: 80

Text #5

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6203. Min Act: -0.1700

Data Index: 3232588 (Open Web Text)

Max Activating Token Index: 857

Text #6

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6253. Min Act: -0.1700

Data Index: 5922174 (Open Web Text)

Max Activating Token Index: 592

Text #7

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6211. Min Act: -0.1700

Data Index: 2162943 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6161. Min Act: -0.1700

Data Index: 7734277 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6069. Min Act: -0.1700

Data Index: 5025794 (Open Web Text)

Max Activating Token Index: 749

Text #10

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6154. Min Act: -0.1700

Data Index: 6854995 (Open Web Text)

Max Activating Token Index: 1001

Text #11

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6138. Min Act: -0.1700

Data Index: 3587693 (Open Web Text)

Max Activating Token Index: 762

Text #12

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6094. Min Act: -0.1700

Data Index: 3692799 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6156. Min Act: -0.1700

Data Index: 7335827 (Open Web Text)

Max Activating Token Index: 266

Text #14

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6032. Min Act: -0.1700

Data Index: 6237036 (Open Web Text)

Max Activating Token Index: 688

Text #15

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6077. Min Act: -0.1700

Data Index: 1948144 (Open Web Text)

Max Activating Token Index: 592

Text #16

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5995. Min Act: -0.1700

Data Index: 2829482 (Open Web Text)

Max Activating Token Index: 268

Text #17

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5883. Min Act: -0.1700

Data Index: 1968936 (Open Web Text)

Max Activating Token Index: 141

Text #18

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.6007. Min Act: -0.1700

Data Index: 108246 (Open Web Text)

Max Activating Token Index: 528

Text #19

Max Range: 1.6794. Min Range: -1.6794

Max Act: 1.5790. Min Act: -0.1700

Data Index: 4463212 (Open Web Text)

Max Activating Token Index: 951