Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5046 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.4033. Min Act: -0.1700
Data Index: 5031243 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.4033. Min Act: -0.1700
Data Index: 942104 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.4033. Min Act: -0.1700
Data Index: 1160811 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.3720. Min Act: -0.1700
Data Index: 230917 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.3720. Min Act: -0.1700
Data Index: 1293937 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.3720. Min Act: -0.1700
Data Index: 5838439 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.3408. Min Act: -0.1700
Data Index: 5192719 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.3095. Min Act: -0.1700
Data Index: 4950288 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.3095. Min Act: -0.1700
Data Index: 7490690 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.3095. Min Act: -0.1700
Data Index: 5232943 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.2783. Min Act: -0.1700
Data Index: 5242285 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.2783. Min Act: -0.1700
Data Index: 4344170 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.2783. Min Act: -0.1700
Data Index: 8499272 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.2783. Min Act: -0.1700
Data Index: 2626010 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.2470. Min Act: -0.1700
Data Index: 6579215 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.2470. Min Act: -0.1700
Data Index: 5878575 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.2470. Min Act: -0.1700
Data Index: 4396798 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.2470. Min Act: -0.1700
Data Index: 8103065 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.1533. Min Act: -0.1700
Data Index: 5760728 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4033. Min Range: -5.4033
Max Act: 5.1845. Min Act: -0.1700
Data Index: 7633790 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19