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

Dataset: Open Web Text

Neuron 2233 in Layer 2

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: 4.1053. Min Range: -4.1053

Max Act: 4.1053. Min Act: -0.1700

Data Index: 495941 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 4.1053. Min Range: -4.1053

Max Act: 4.0189. Min Act: -0.1700

Data Index: 7708839 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.9705. Min Act: -0.1700

Data Index: 4141761 (Open Web Text)

Max Activating Token Index: 142

Text #3

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.9327. Min Act: -0.1700

Data Index: 2743848 (Open Web Text)

Max Activating Token Index: 98

Text #4

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8933. Min Act: -0.1700

Data Index: 4570468 (Open Web Text)

Max Activating Token Index: 74

Text #5

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8539. Min Act: -0.1700

Data Index: 1808005 (Open Web Text)

Max Activating Token Index: 472

Text #6

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8966. Min Act: -0.1700

Data Index: 4963948 (Open Web Text)

Max Activating Token Index: 271

Text #7

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.9090. Min Act: -0.1700

Data Index: 4690504 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8801. Min Act: -0.1700

Data Index: 3687843 (Open Web Text)

Max Activating Token Index: 489

Text #9

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8823. Min Act: -0.1700

Data Index: 5913101 (Open Web Text)

Max Activating Token Index: 151

Text #10

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.9084. Min Act: -0.1700

Data Index: 3584402 (Open Web Text)

Max Activating Token Index: 558

Text #11

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8626. Min Act: -0.1700

Data Index: 5135809 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8544. Min Act: -0.1700

Data Index: 2743850 (Open Web Text)

Max Activating Token Index: 708

Text #13

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8330. Min Act: -0.1700

Data Index: 236828 (Open Web Text)

Max Activating Token Index: 581

Text #14

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8135. Min Act: -0.1700

Data Index: 302436 (Open Web Text)

Max Activating Token Index: 677

Text #15

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.7706. Min Act: -0.1700

Data Index: 7548129 (Open Web Text)

Max Activating Token Index: 394

Text #16

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.8017. Min Act: -0.1700

Data Index: 4324079 (Open Web Text)

Max Activating Token Index: 163

Text #17

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.7607. Min Act: -0.1700

Data Index: 5183723 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.7865. Min Act: -0.1700

Data Index: 3836642 (Open Web Text)

Max Activating Token Index: 209

Text #19

Max Range: 4.1053. Min Range: -4.1053

Max Act: 3.7841. Min Act: -0.1700

Data Index: 5670758 (Open Web Text)

Max Activating Token Index: 583