Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.6948. Min Act: -0.1700
Data Index: 6532506 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.7261. Min Act: -0.1700
Data Index: 2946099 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.6948. Min Act: -0.1700
Data Index: 4661065 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.7261. Min Act: -0.1700
Data Index: 6554756 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.6011. Min Act: -0.1700
Data Index: 7368277 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5698. Min Act: -0.1700
Data Index: 1444488 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5698. Min Act: -0.1700
Data Index: 2644996 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5386. Min Act: -0.1700
Data Index: 2513301 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5073. Min Act: -0.1700
Data Index: 6800813 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5386. Min Act: -0.1700
Data Index: 3244198 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5698. Min Act: -0.1700
Data Index: 5892452 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5386. Min Act: -0.1700
Data Index: 23862 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5386. Min Act: -0.1700
Data Index: 4419590 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5073. Min Act: -0.1700
Data Index: 8703043 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5073. Min Act: -0.1700
Data Index: 8168686 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5073. Min Act: -0.1700
Data Index: 2163876 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5073. Min Act: -0.1700
Data Index: 6915892 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.4761. Min Act: -0.1700
Data Index: 5800258 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.4761. Min Act: -0.1700
Data Index: 7287458 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7261. Min Range: -4.7261
Max Act: 4.5073. Min Act: -0.1700
Data Index: 2409342 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19