Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4262 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0977. Min Range: -6.0977
Max Act: 6.0977. Min Act: -0.1700
Data Index: 5906230 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0977. Min Range: -6.0977
Max Act: 6.0352. Min Act: -0.1700
Data Index: 5460747 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.9727. Min Act: -0.1700
Data Index: 4256322 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.9727. Min Act: -0.1700
Data Index: 861354 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.9102. Min Act: -0.1700
Data Index: 5293558 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8789. Min Act: -0.1700
Data Index: 256229 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8789. Min Act: -0.1700
Data Index: 5460746 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8477. Min Act: -0.1700
Data Index: 3481822 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8477. Min Act: -0.1700
Data Index: 174274 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8789. Min Act: -0.1700
Data Index: 6437369 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8477. Min Act: -0.1700
Data Index: 7358478 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7852. Min Act: -0.1700
Data Index: 1811642 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8164. Min Act: -0.1699
Data Index: 407045 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8164. Min Act: -0.1700
Data Index: 3812840 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8164. Min Act: -0.1700
Data Index: 6641841 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8164. Min Act: -0.1700
Data Index: 256227 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.8164. Min Act: -0.1700
Data Index: 2624777 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7852. Min Act: -0.1700
Data Index: 5138659 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7852. Min Act: -0.1700
Data Index: 6506177 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0977. Min Range: -6.0977
Max Act: 5.7852. Min Act: -0.1700
Data Index: 6508830 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19