Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 582 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0254. Min Range: -6.0254
Max Act: 6.0254. Min Act: -0.1700
Data Index: 5646395 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.9317. Min Act: -0.1700
Data Index: 5662207 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.9004. Min Act: -0.1700
Data Index: 5668760 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.8692. Min Act: -0.1700
Data Index: 1283840 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7754. Min Act: -0.1700
Data Index: 6238757 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7442. Min Act: -0.1700
Data Index: 4828006 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7754. Min Act: -0.1700
Data Index: 5924511 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7442. Min Act: -0.1700
Data Index: 4125718 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7442. Min Act: -0.1700
Data Index: 8133076 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7442. Min Act: -0.1700
Data Index: 2768173 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7129. Min Act: -0.1700
Data Index: 1895750 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7129. Min Act: -0.1700
Data Index: 2490156 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.6817. Min Act: -0.1700
Data Index: 3749206 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7129. Min Act: -0.1700
Data Index: 952215 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.6817. Min Act: -0.1700
Data Index: 7946034 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.7129. Min Act: -0.1700
Data Index: 2832686 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.6504. Min Act: -0.1700
Data Index: 8497028 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.6192. Min Act: -0.1700
Data Index: 4276868 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.6504. Min Act: -0.1700
Data Index: 8364289 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0254. Min Range: -6.0254
Max Act: 5.5879. Min Act: -0.1700
Data Index: 2768170 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19