Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.8571. Min Act: -0.1700
Data Index: 146485 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.8571. Min Act: -0.1700
Data Index: 7759773 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7946. Min Act: -0.1700
Data Index: 6905666 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.8259. Min Act: -0.1700
Data Index: 4955532 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.8259. Min Act: -0.1700
Data Index: 7444445 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.8259. Min Act: -0.1700
Data Index: 352759 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7946. Min Act: -0.1700
Data Index: 1150038 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7946. Min Act: -0.1700
Data Index: 7436895 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7946. Min Act: -0.1700
Data Index: 7444443 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7946. Min Act: -0.1700
Data Index: 5925658 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7946. Min Act: -0.1700
Data Index: 4484435 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7634. Min Act: -0.1700
Data Index: 7577337 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7634. Min Act: -0.1700
Data Index: 2203028 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 7753198 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7009. Min Act: -0.1700
Data Index: 2377930 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 854117 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 6732050 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7634. Min Act: -0.1700
Data Index: 6064879 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 562477 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 2196100 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19