Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.3666. Min Act: -0.1700
Data Index: 6391199 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.3666. Min Act: -0.1700
Data Index: 3703323 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.3353. Min Act: -0.1700
Data Index: 7692745 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.2103. Min Act: -0.1700
Data Index: 1233513 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.1791. Min Act: -0.1700
Data Index: 3925740 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.1791. Min Act: -0.1700
Data Index: 8502951 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.1478. Min Act: -0.1700
Data Index: 6839927 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.1478. Min Act: -0.1700
Data Index: 7996276 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.1478. Min Act: -0.1700
Data Index: 1902931 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.1165. Min Act: -0.1700
Data Index: 667219 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0540. Min Act: -0.1700
Data Index: 5204472 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0853. Min Act: -0.1700
Data Index: 1141476 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0853. Min Act: -0.1700
Data Index: 6929274 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0853. Min Act: -0.1700
Data Index: 176955 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0853. Min Act: -0.1700
Data Index: 3682090 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0540. Min Act: -0.1700
Data Index: 4784800 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0540. Min Act: -0.1700
Data Index: 6012622 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0540. Min Act: -0.1700
Data Index: 6704360 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3666. Min Range: -4.3666
Max Act: 4.0228. Min Act: -0.1700
Data Index: 1686990 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3666. Min Range: -4.3666
Max Act: 3.9915. Min Act: -0.1700
Data Index: 7762857 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19