Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.4911. Min Act: -0.1700
Data Index: 6044536 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.4599. Min Act: -0.1700
Data Index: 796810 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.4286. Min Act: -0.1700
Data Index: 54701 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.3349. Min Act: -0.1700
Data Index: 8110815 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.3349. Min Act: -0.1700
Data Index: 4918602 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.3036. Min Act: -0.1700
Data Index: 8172209 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.2724. Min Act: -0.1700
Data Index: 415813 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.2411. Min Act: -0.1700
Data Index: 7818167 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.2411. Min Act: -0.1700
Data Index: 4321287 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.2099. Min Act: -0.1700
Data Index: 8722100 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.2099. Min Act: -0.1700
Data Index: 3857358 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.2411. Min Act: -0.1700
Data Index: 8433836 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.1786. Min Act: -0.1700
Data Index: 6005391 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.1786. Min Act: -0.1700
Data Index: 3998499 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.1786. Min Act: -0.1700
Data Index: 871849 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.1474. Min Act: -0.1700
Data Index: 5108599 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.1474. Min Act: -0.1700
Data Index: 7641868 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.0849. Min Act: -0.1700
Data Index: 5994045 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.1161. Min Act: -0.1700
Data Index: 8393935 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4911. Min Range: -4.4911
Max Act: 4.1161. Min Act: -0.1700
Data Index: 3600315 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19