Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 833 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.8694. Min Act: -0.1700
Data Index: 8049703 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.8381. Min Act: -0.1700
Data Index: 6014790 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.7756. Min Act: -0.1700
Data Index: 4517366 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.7444. Min Act: -0.1700
Data Index: 1126872 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.7131. Min Act: -0.1700
Data Index: 1771176 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.6819. Min Act: -0.1700
Data Index: 2006851 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.6819. Min Act: -0.1700
Data Index: 1404198 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.6194. Min Act: -0.1700
Data Index: 5791364 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.5881. Min Act: -0.1700
Data Index: 8579421 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.5881. Min Act: -0.1700
Data Index: 8605696 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.6194. Min Act: -0.1700
Data Index: 5849191 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.5256. Min Act: -0.1700
Data Index: 6175757 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.5569. Min Act: -0.1700
Data Index: 1804664 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.4944. Min Act: -0.1700
Data Index: 723544 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.5256. Min Act: -0.1700
Data Index: 2822357 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.4944. Min Act: -0.1700
Data Index: 3128207 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.4631. Min Act: -0.1700
Data Index: 1793779 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.4006. Min Act: -0.1700
Data Index: 149536 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.4631. Min Act: -0.1700
Data Index: 5981162 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8694. Min Range: -5.8694
Max Act: 5.4006. Min Act: -0.1700
Data Index: 3011955 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19