Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.3258. Min Act: -0.1700
Data Index: 3770806 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.3258. Min Act: -0.1700
Data Index: 1210997 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.2008. Min Act: -0.1700
Data Index: 6045632 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.2008. Min Act: -0.1700
Data Index: 5123244 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1696. Min Act: -0.1700
Data Index: 4895079 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1696. Min Act: -0.1700
Data Index: 3828689 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1696. Min Act: -0.1700
Data Index: 4755006 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1383. Min Act: -0.1700
Data Index: 113938 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1383. Min Act: -0.1700
Data Index: 6887902 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 5187480 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1383. Min Act: -0.1700
Data Index: 5621522 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 5409191 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 4576032 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 705314 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 7670204 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 7396742 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 5077903 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 6320173 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 1463214 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3258. Min Range: -5.3258
Max Act: 5.1071. Min Act: -0.1700
Data Index: 3767849 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19