Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.5790. Min Act: -0.1700
Data Index: 2546417 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.5007. Min Act: -0.1700
Data Index: 4142524 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.4850. Min Act: -0.1700
Data Index: 4037540 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.4537. Min Act: -0.1700
Data Index: 4280337 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.4537. Min Act: -0.1700
Data Index: 4230249 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.4380. Min Act: -0.1700
Data Index: 8455396 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.4067. Min Act: -0.1700
Data Index: 3353622 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.4067. Min Act: -0.1700
Data Index: 5422281 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.4067. Min Act: -0.1700
Data Index: 8690701 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3753. Min Act: -0.1700
Data Index: 5604628 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3910. Min Act: -0.1700
Data Index: 2908200 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3910. Min Act: -0.1700
Data Index: 1540273 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3910. Min Act: -0.1700
Data Index: 2955849 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3753. Min Act: -0.1700
Data Index: 6822050 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3753. Min Act: -0.1700
Data Index: 462887 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3596. Min Act: -0.1700
Data Index: 3506018 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3910. Min Act: -0.1700
Data Index: 3658542 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3910. Min Act: -0.1700
Data Index: 7413265 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3753. Min Act: -0.1700
Data Index: 2006830 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5790. Min Range: -3.5790
Max Act: 3.3596. Min Act: -0.1700
Data Index: 2609678 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19