Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 502 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.5500. Min Act: -0.1700
Data Index: 3268748 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.5339. Min Act: -0.1700
Data Index: 3243769 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.5339. Min Act: -0.1700
Data Index: 2792109 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.5177. Min Act: -0.1700
Data Index: 998190 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.5015. Min Act: -0.1700
Data Index: 2612597 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.4528. Min Act: -0.1700
Data Index: 5241292 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.4528. Min Act: -0.1700
Data Index: 6044830 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.4203. Min Act: -0.1700
Data Index: 2871363 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3713. Min Act: -0.1700
Data Index: 6883434 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3877. Min Act: -0.1700
Data Index: 7794012 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3877. Min Act: -0.1700
Data Index: 14944 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3877. Min Act: -0.1700
Data Index: 6087631 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3877. Min Act: -0.1700
Data Index: 4658326 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3713. Min Act: -0.1700
Data Index: 7378873 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3877. Min Act: -0.1700
Data Index: 3918015 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.4040. Min Act: -0.1700
Data Index: 1417980 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3877. Min Act: -0.1700
Data Index: 14943 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3550. Min Act: -0.1700
Data Index: 7838518 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3713. Min Act: -0.1700
Data Index: 5776915 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5500. Min Range: -2.5500
Max Act: 2.3713. Min Act: -0.1700
Data Index: 1811980 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19