Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.7530. Min Act: -0.1700
Data Index: 2245671 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.7217. Min Act: -0.1700
Data Index: 3940237 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.7217. Min Act: -0.1700
Data Index: 1050716 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.7217. Min Act: -0.1700
Data Index: 5672589 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.7217. Min Act: -0.1700
Data Index: 5753264 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.7217. Min Act: -0.1700
Data Index: 1695090 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 3388746 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 3781821 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 1284454 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.7217. Min Act: -0.1700
Data Index: 7698193 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 1796862 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 6422691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 577363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 5329379 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 5034267 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 3874626 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 776364 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 2111217 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6904. Min Act: -0.1700
Data Index: 1978003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7530. Min Range: -3.7530
Max Act: 3.6592. Min Act: -0.1700
Data Index: 1817327 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19