Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 89 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.5901. Min Act: -0.1700
Data Index: 1021165 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.3401. Min Act: -0.1700
Data Index: 5879756 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.2776. Min Act: -0.1700
Data Index: 5962212 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.3401. Min Act: -0.1700
Data Index: 1933195 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.1213. Min Act: -0.1700
Data Index: 7642953 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.1526. Min Act: -0.1700
Data Index: 5328930 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.0901. Min Act: -0.1700
Data Index: 3282986 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.0276. Min Act: -0.1700
Data Index: 4994476 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.0588. Min Act: -0.1700
Data Index: 3093088 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.9963. Min Act: -0.1700
Data Index: 328724 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.0276. Min Act: -0.1700
Data Index: 1473271 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.9651. Min Act: -0.1700
Data Index: 3233481 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5901. Min Range: -7.5901
Max Act: 7.0276. Min Act: -0.1700
Data Index: 8609411 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.9651. Min Act: -0.1700
Data Index: 131469 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.9338. Min Act: -0.1700
Data Index: 4626265 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.8713. Min Act: -0.1700
Data Index: 1780749 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.9026. Min Act: -0.1700
Data Index: 4726644 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.9338. Min Act: -0.1700
Data Index: 4424035 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.9338. Min Act: -0.1700
Data Index: 2050220 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5901. Min Range: -7.5901
Max Act: 6.8713. Min Act: -0.1700
Data Index: 5986896 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19