Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 975 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7111. Min Range: -9.7111
Max Act: 9.7111. Min Act: -0.1700
Data Index: 7929904 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7111. Min Range: -9.7111
Max Act: 9.2736. Min Act: -0.1700
Data Index: 6392498 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7111. Min Range: -9.7111
Max Act: 9.2111. Min Act: -0.1700
Data Index: 1102875 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7111. Min Range: -9.7111
Max Act: 9.0861. Min Act: -0.1700
Data Index: 7170918 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7111. Min Range: -9.7111
Max Act: 9.0236. Min Act: -0.1700
Data Index: 7113655 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7111. Min Range: -9.7111
Max Act: 9.0236. Min Act: -0.1700
Data Index: 999332 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7111. Min Range: -9.7111
Max Act: 9.0236. Min Act: -0.1700
Data Index: 153962 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7111. Min Range: -9.7111
Max Act: 9.0236. Min Act: -0.1700
Data Index: 2304594 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.9611. Min Act: -0.1700
Data Index: 617528 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.8986. Min Act: -0.1700
Data Index: 2832271 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.8361. Min Act: -0.1700
Data Index: 483697 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.8986. Min Act: -0.1700
Data Index: 673512 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.8986. Min Act: -0.1700
Data Index: 4916241 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.8361. Min Act: -0.1700
Data Index: 1734269 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.8361. Min Act: -0.1700
Data Index: 3089685 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.7736. Min Act: -0.1700
Data Index: 6048332 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.7736. Min Act: -0.1700
Data Index: 2252909 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.7736. Min Act: -0.1700
Data Index: 7254315 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.7111. Min Act: -0.1700
Data Index: 1140652 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7111. Min Range: -9.7111
Max Act: 8.7111. Min Act: -0.1700
Data Index: 3745536 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19